Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

The first natively trained 1-bit model: BitNet 2B. Trained on 4 trillion tokens. that can run on CPUs like Apple M2 Native 1.58-bit weights and 8bit activations W158A8 Outperforms LLaMA &close to Qwen 2.5 1.5B in while using only 0.4GB memory versus 2GB and processes tokens 40%

Md Ismail Šojal 🕷️

44,919 subscribers

43,647 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥 > Zero-shot voice cloning > Emotional TTS > Trained on 100K hours of data > Long form synthesis > Variable speed synthesis > Bilingual - Chinese & English > Available on Hugging Face Fully non-autoregressive architecture: > Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model > Stage 2: Predicts acoustic tokens conditioned on the semantic tokens. Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!" TTS scene keeps getting lit! 🐐

Fuck yeah! MaskGCT - New open SoTA Text to Speech model! 🔥 > Zero-shot voice cloning > Emotional TTS > Trained on 100K hours of data > Long form synthesis > Variable speed synthesis > Bilingual - Chinese & English > Available on Hugging Face Fully non-autoregressive architecture: > Stage 1: Predicts semantic tokens from text, using tokens extracted from a speech self-supervised learning (SSL) model > Stage 2: Predicts acoustic tokens conditioned on the semantic tokens. Synthesised: "Would you guys personally like to have a fake fireplace, an electric one, in your house? Or would you rather have a real fireplace? Let me know down below. Okay everybody, that's all for today's video and I hope you guys learned a bunch of furniture vocabulary!" TTS scene keeps getting lit! 🐐

Vaibhav (VB) Srivastav

139,085 views • 1 year ago

AN AWS ENGINEER QUIETLY BUILT A 2 PETABYTE HOME SERVER FOR $9/MONTH THAT KILLS A $3,400/MONTH CLOUD STORAGE BILL the lenovo thinkstation pgx ships nvidia's gb10 grace blackwell superchip and 128gb of unified memory in a box the size of a mac mini at 1.2kg it runs an 80b qwen3 coder model at 25 to 40 tokens per second and a 196b step-3.5-flash moe model at 20 tokens per second locally the gb10 packs 6,144 cuda cores, 192 fifth-generation tensor cores and rates at 1 petaflop of fp4 with sparsity from a single 240 watt usb-c power supply fine tuning qwen 2.5 7b with lora took 18 minutes and 41gb of unified memory while the gpu pulled 65 watts and peaked at 77 degrees the box pulls a docker container from nvidia's registry and serves a frontier model on your local network with tool calling and zero data leaving your desk bookmark this and read the article below

AN AWS ENGINEER QUIETLY BUILT A 2 PETABYTE HOME SERVER FOR $9/MONTH THAT KILLS A $3,400/MONTH CLOUD STORAGE BILL the lenovo thinkstation pgx ships nvidia's gb10 grace blackwell superchip and 128gb of unified memory in a box the size of a mac mini at 1.2kg it runs an 80b qwen3 coder model at 25 to 40 tokens per second and a 196b step-3.5-flash moe model at 20 tokens per second locally the gb10 packs 6,144 cuda cores, 192 fifth-generation tensor cores and rates at 1 petaflop of fp4 with sparsity from a single 240 watt usb-c power supply fine tuning qwen 2.5 7b with lora took 18 minutes and 41gb of unified memory while the gpu pulled 65 watts and peaked at 77 degrees the box pulls a docker container from nvidia's registry and serves a frontier model on your local network with tool calling and zero data leaving your desk bookmark this and read the article below

starmex

192,225 views • 1 month ago

✨ Every week a new AI model comes out and it suddenly makes my half broken features work a lot better Yesterday Seedream-4-Edit came out and it made my [ Hold product ] feature on Photo AI a lot better You can now go from: 🎁 Product photo -> 👱‍♀️ Talking video with your AI model while holding your product. In just a few minutes! Here's a photo I took from the weekly farm box we get in our kitchen, I set it as the product and then with Photo AI made it into a talking video where my trained AI model presents it It's not perfect, as the objects inside the farm box still move around a bit, but pretty close. If the product is more uniform (like lip gloss, a product box or a book) it does a pretty good job at keeping it exactly the same This "consistency" as they call it is quite important for actual real world use. Product sellers don't want to have an image or video of an AI model if the product doesn't look exactly the same as what they sell With that, I'm getting pretty close now and every week with every new model that comes out, a bit closer And it's interesting cause now I'm finally moving from B2C a bit more to B2B where businesses can use Photo AI more, designers and stores already use it for trying on clothes etc. but now they can generate content for real products! 😊 LIVE now on Photo AI

✨ Every week a new AI model comes out and it suddenly makes my half broken features work a lot better Yesterday Seedream-4-Edit came out and it made my [ Hold product ] feature on Photo AI a lot better You can now go from: 🎁 Product photo -> 👱‍♀️ Talking video with your AI model while holding your product. In just a few minutes! Here's a photo I took from the weekly farm box we get in our kitchen, I set it as the product and then with Photo AI made it into a talking video where my trained AI model presents it It's not perfect, as the objects inside the farm box still move around a bit, but pretty close. If the product is more uniform (like lip gloss, a product box or a book) it does a pretty good job at keeping it exactly the same This "consistency" as they call it is quite important for actual real world use. Product sellers don't want to have an image or video of an AI model if the product doesn't look exactly the same as what they sell With that, I'm getting pretty close now and every week with every new model that comes out, a bit closer And it's interesting cause now I'm finally moving from B2C a bit more to B2B where businesses can use Photo AI more, designers and stores already use it for trying on clothes etc. but now they can generate content for real products! 😊 LIVE now on Photo AI

@levelsio

361,558 views • 10 months ago

🚨 RWA PAD PLATFORM LIVE AND FIRST PROJECTS COMPETE ON DEMODAY 🚨 Hello EstateX Family, RWA Pad platform is live. Because of the tech teams occupation there are still some changes made to the website and the content is not completely final. To be able to participate in the projects that will be coming on RWA Pad, you need to hold or lock $ESX. The following tiers qualify, with Tier 5 having first access AND getting the best deal. Tier 5: Unicorn Club (1M+ tokens) Tier 4: 500,000 tokens Tier 3: 100,000 tokens Tier 2: 50,000 tokens Tier 1: 10,000 tokens This also means that new investors / their community need to buy $ESX to participate. 🚨 DEMO DAY ON THE 17TH OF FEBRUARY On the 17th of February, the first projects will compete for a spot on the launchpad. These projects will bring their audience, and judges will be our (famous) project partners and KOLs. On top of that, the EstateX Family will have a decisive vote on the projects that they want to see on the launchpad. In a battle style form, they will compete and create content, viral moments and bring audience. A week later the first raise will happen on RWA Pad, followed by buyback of the revenue generated. No matter what happens, the team keeps showing up. On Monday we have the L1 chain Beta launch with a Graham AMA, we have Sky Villa’s opening up, other property payments opening up with continued sales, the demo day, RWA Pad raise with all followed by generated revenue buybacks. Make sure to watch today’s AMA as we also discussed price action, the team, the switching of legal framework to make property sales more efficient (hence the delay), how the team moves forward and what’s upcoming. 🚨 REGISTER FOR YOUR TIER ON RWA PAD You can register for your tier on RWA Pad now, by selecting one of the five. Click register now on the site below. *Content is not finalized yet and subject to change. We are also curious if you want to see other sectors apart from RWA (like AI, perps, prediction markets, privacy tokens or anything else). Let us know below 👇

🚨 RWA PAD PLATFORM LIVE AND FIRST PROJECTS COMPETE ON DEMODAY 🚨 Hello EstateX Family, RWA Pad platform is live. Because of the tech teams occupation there are still some changes made to the website and the content is not completely final. To be able to participate in the projects that will be coming on RWA Pad, you need to hold or lock $ESX. The following tiers qualify, with Tier 5 having first access AND getting the best deal. Tier 5: Unicorn Club (1M+ tokens) Tier 4: 500,000 tokens Tier 3: 100,000 tokens Tier 2: 50,000 tokens Tier 1: 10,000 tokens This also means that new investors / their community need to buy $ESX to participate. 🚨 DEMO DAY ON THE 17TH OF FEBRUARY On the 17th of February, the first projects will compete for a spot on the launchpad. These projects will bring their audience, and judges will be our (famous) project partners and KOLs. On top of that, the EstateX Family will have a decisive vote on the projects that they want to see on the launchpad. In a battle style form, they will compete and create content, viral moments and bring audience. A week later the first raise will happen on RWA Pad, followed by buyback of the revenue generated. No matter what happens, the team keeps showing up. On Monday we have the L1 chain Beta launch with a Graham AMA, we have Sky Villa’s opening up, other property payments opening up with continued sales, the demo day, RWA Pad raise with all followed by generated revenue buybacks. Make sure to watch today’s AMA as we also discussed price action, the team, the switching of legal framework to make property sales more efficient (hence the delay), how the team moves forward and what’s upcoming. 🚨 REGISTER FOR YOUR TIER ON RWA PAD You can register for your tier on RWA Pad now, by selecting one of the five. Click register now on the site below. *Content is not finalized yet and subject to change. We are also curious if you want to see other sectors apart from RWA (like AI, perps, prediction markets, privacy tokens or anything else). Let us know below 👇

EstateX

83,238 views • 5 months ago

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Pascale Fung

90,144 views • 7 months ago

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

Alok

292,096 views • 1 month ago

🚀 Update Next Scene V2 only 10 days after last version, now live on Hugging Face 👉 🎬 A LoRA made for Qwen Image Edit 2509 that lets you create seamless cinematic “next shots” — keeping the same characters, lighting, and mood. I trained this new version on thousands of paired cinematic shots to make scene transitions smoother, more emotional, and real. 🧠 What’s new: • Much stronger consistency across shots • Better lighting and character preservation • Smoother transitions and framing logic • No more black bar artifacts Built for storytellers using ComfyUI or any diffusers pipeline. Just use “Next Scene:” and describe what happens next , the model keeps everything coherent. 🧩 Try it directly in ComfyUI, or check the thread to launch it on fal . Open-source, no restrictions, made for filmmakers, animators, and dreamers. ComfyUI #AIcinema #LoRA #Flux #Qwen #ComfyUI #AIart #GenerativeVideo you can test on comfyui or to try on you can go here : and use my lora link : start your prompt with "Next Scene:" and lets go !!

🚀 Update Next Scene V2 only 10 days after last version, now live on Hugging Face 👉 🎬 A LoRA made for Qwen Image Edit 2509 that lets you create seamless cinematic “next shots” — keeping the same characters, lighting, and mood. I trained this new version on thousands of paired cinematic shots to make scene transitions smoother, more emotional, and real. 🧠 What’s new: • Much stronger consistency across shots • Better lighting and character preservation • Smoother transitions and framing logic • No more black bar artifacts Built for storytellers using ComfyUI or any diffusers pipeline. Just use “Next Scene:” and describe what happens next , the model keeps everything coherent. 🧩 Try it directly in ComfyUI, or check the thread to launch it on fal . Open-source, no restrictions, made for filmmakers, animators, and dreamers. ComfyUI #AIcinema #LoRA #Flux #Qwen #ComfyUI #AIart #GenerativeVideo you can test on comfyui or to try on you can go here : and use my lora link : start your prompt with "Next Scene:" and lets go !!

Lovis Odin

43,276 views • 9 months ago

This Chinese developer launched Llama 70B locally on a MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.

This Chinese developer launched Llama 70B locally on a MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.

Blaze

1,838,219 views • 2 months ago

🚨 Do you understand what Claude just quietly dropped while everyone was distracted? 1 million tokens. Let me explain what that actually means because the number alone doesn't hit right. > A senior engineer joins a company and spends 3 to 6 months just reading code.. Understanding how things connect. Learning where the bugs hide. Why that one file nobody touches exists. It takes months because a codebase is massive and human memory is small. > Claude just loaded the entire thing in one prompt. 30 seconds. Every file, Every function, Every line. All of it. Sitting in memory like it's been working there for years. And it scored highest among every single frontier model. Not GPT.. Not Gemini, Nobody. > Yesterday Amazon's AI nuked production because it couldn't see the full picture - it made a decision with partial context and deleted everything. Today an AI can hold 1 million tokens of context at once. That's the fix. That's the "before and after" moment for AI coding. > 600 images in one request. Entire PDFs. Full repos. And they dropped it on a Friday on all plans like it was a patch note. The scariest AI updates aren't the ones with press conferences. They're the ones that drop in a tweet at 6pm and change everything by Monday morning.

🚨 Do you understand what Claude just quietly dropped while everyone was distracted? 1 million tokens. Let me explain what that actually means because the number alone doesn't hit right. > A senior engineer joins a company and spends 3 to 6 months just reading code.. Understanding how things connect. Learning where the bugs hide. Why that one file nobody touches exists. It takes months because a codebase is massive and human memory is small. > Claude just loaded the entire thing in one prompt. 30 seconds. Every file, Every function, Every line. All of it. Sitting in memory like it's been working there for years. And it scored highest among every single frontier model. Not GPT.. Not Gemini, Nobody. > Yesterday Amazon's AI nuked production because it couldn't see the full picture - it made a decision with partial context and deleted everything. Today an AI can hold 1 million tokens of context at once. That's the fix. That's the "before and after" moment for AI coding. > 600 images in one request. Entire PDFs. Full repos. And they dropped it on a Friday on all plans like it was a patch note. The scariest AI updates aren't the ones with press conferences. They're the ones that drop in a tweet at 6pm and change everything by Monday morning.

Tuki

206,260 views • 4 months ago

This lawyer made $150,000 selling portable offline AI. It analyzes docs that can’t legally be shown on the web. The whole setup costs $50 and he sells it for $999. Here's how to make one step-by-step: You need 4 things: → Raspberry Pi 5 (8GB) → PiSugar 3 Plus battery → Whisplay HAT for the screen and mic → 64GB SD card. Total cost on Ali is around $50 to $90 if you wait for the right deals. 1. Write Raspberry Pi OS Lite 64-bit to the SD card using Raspberry Pi Imager. 2. Stack the PiSugar battery underneath the Pi, snap the Whisplay HAT on top, insert the SD card, and boot the device. 3. Open the terminal and install Ollama with one command: curl -fsSL | sh 4. Pull a model that actually runs on the Pi without choking: ollama pull phi3:mini 5. Run the model and start chatting offline: ollama run phi3:mini The whole thing fits in your pocket, lasts 4 hours on battery, and never touches the internet once setup is done. The lawyer wraps his version in a custom case, preloads it with legal document analysis prompts, and sells it to law firms that can't legally process client data in the cloud. You can sell yours to doctors, accountants, government contractors, defense companies, or anyone else who handles data that legally cannot leave the building. Hardware cost: $50 to $90. Selling price: $500 to $1999

This lawyer made $150,000 selling portable offline AI. It analyzes docs that can’t legally be shown on the web. The whole setup costs $50 and he sells it for $999. Here's how to make one step-by-step: You need 4 things: → Raspberry Pi 5 (8GB) → PiSugar 3 Plus battery → Whisplay HAT for the screen and mic → 64GB SD card. Total cost on Ali is around $50 to $90 if you wait for the right deals. 1. Write Raspberry Pi OS Lite 64-bit to the SD card using Raspberry Pi Imager. 2. Stack the PiSugar battery underneath the Pi, snap the Whisplay HAT on top, insert the SD card, and boot the device. 3. Open the terminal and install Ollama with one command: curl -fsSL | sh 4. Pull a model that actually runs on the Pi without choking: ollama pull phi3:mini 5. Run the model and start chatting offline: ollama run phi3:mini The whole thing fits in your pocket, lasts 4 hours on battery, and never touches the internet once setup is done. The lawyer wraps his version in a custom case, preloads it with legal document analysis prompts, and sells it to law firms that can't legally process client data in the cloud. You can sell yours to doctors, accountants, government contractors, defense companies, or anyone else who handles data that legally cannot leave the building. Hardware cost: $50 to $90. Selling price: $500 to $1999

Coin Shot ☁️

199,276 views • 1 month ago

my 8 GB VRAM gaming laptop is absolutely going to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 31b Q4) with only 8 GB VRAM last week I ran Gemma 4 26B A4B a mixture of experts model on my RTX 4060 and hit 25–28 tokens/sec using llama.cpp's new MTP support. smooth. snappy. but MoE has a secret: it only activates 4B parameters per token despite having 26B total. that's why it flies. so the real question started haunting me. what if I throw a full, no tricks, every parameter fires on every token, 31B DENSE model at the same machine? # Hardware: GPU: NVIDIA RTX 4060, 8 GB VRAM RAM: 16 GB CPU: Intel Core i7 H Laptop. Gaming. Modest. The model: gemma-4-31B-it-qat-UD-Q4_K_XL.gguf (model's unsloth huggingface link in the comments) This is Google DeepMind's flagship dense model in the Gemma 4 family that can run on single consumer GPU. It packs a hybrid attention architecture, supports up to 256K context natively, and is QAT (Quantization Aware Training) optimized, meaning it retains far more quality than standard post training quants at the same bit depth. This is NOT the MoE. This is 31 BILLION dense parameters, every single one of them loaded. # the flags I used: -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -cnv --spec-type draft-mtp --spec-draft-model mtp-gemma-4-31B-it.gguf --spec-draft-n-max 8 --spec-draft-p-min 0.6 -c 6000 -v Multi Token Prediction (MTP) is still active here. Separate draft GGUF required, same as the 26B setup. # Results: → Decode: ~3 tokens/sec → Prefill: ~2 tokens/sec → Context: 6000 tokens → Hardware crying quietly in the corner: yes so is 3 tps actually usable? For real time back and forth chat? Not ideal. You're not having a fluid conversation at 3 tps. but slow ≠ useless. And this is where it gets genuinely interesting. think about how senior devs actually work in a real team. But when something is architectural, deeply complex, or needs serious reasoning? they walk down the hall and escalate to the senior. That's exactly the local AI agent architecture this unlocks: → Fast orchestrator model (Gemma 4 26B MoE at 25+ tps) handles routing, simple queries, tool calls, memory. The junior dev. → Gemma 4 31B dense is the senior, called only when the fast model genuinely hits a wall. Hard multi step reasoning. Complex code generation. Deep architectural decisions. The agentic loop stays fast. Only the hard hops touch the 31B. That's a legitimate production grade local AI architecture on a budget hardware. (requires 2 8gb gpus) other workflows where 3 tps is completely fine: - overnight batch jobs. summarize documents, extract structured data, review code. Fire it off. Sleep. wake up to results. - One shot deep reasoning - Silent code audit loops, you write and test, the 31B reviews diffs and flags issues in the background between your sprints - Any workflow where output quality > output speed A few weeks ago, nobody was running a 30B+ dense model on a single consumer GPU with 8 GB VRAM. At all. Now we're doing it on an Intel i7-H gaming laptop with a NVIDIA RTX 4060, thanks to llama.cpp + QAT quants + MTP speculative drafting. Google DeepMind said the Gemma 4 31B targets "consumer GPUs and workstations." They were not exaggerating. The hardware bar to run serious frontier class models locally keeps dropping. the tools are here. the models are here. you just have to be willing to abuse your laptop a little. what workflows would you actually run on a local 3 tps 31B dense model? genuinely curious. drop it below.

my 8 GB VRAM gaming laptop is absolutely going to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 31b Q4) with only 8 GB VRAM last week I ran Gemma 4 26B A4B a mixture of experts model on my RTX 4060 and hit 25–28 tokens/sec using llama.cpp's new MTP support. smooth. snappy. but MoE has a secret: it only activates 4B parameters per token despite having 26B total. that's why it flies. so the real question started haunting me. what if I throw a full, no tricks, every parameter fires on every token, 31B DENSE model at the same machine? # Hardware: GPU: NVIDIA RTX 4060, 8 GB VRAM RAM: 16 GB CPU: Intel Core i7 H Laptop. Gaming. Modest. The model: gemma-4-31B-it-qat-UD-Q4_K_XL.gguf (model's unsloth huggingface link in the comments) This is Google DeepMind's flagship dense model in the Gemma 4 family that can run on single consumer GPU. It packs a hybrid attention architecture, supports up to 256K context natively, and is QAT (Quantization Aware Training) optimized, meaning it retains far more quality than standard post training quants at the same bit depth. This is NOT the MoE. This is 31 BILLION dense parameters, every single one of them loaded. # the flags I used: -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -cnv --spec-type draft-mtp --spec-draft-model mtp-gemma-4-31B-it.gguf --spec-draft-n-max 8 --spec-draft-p-min 0.6 -c 6000 -v Multi Token Prediction (MTP) is still active here. Separate draft GGUF required, same as the 26B setup. # Results: → Decode: ~3 tokens/sec → Prefill: ~2 tokens/sec → Context: 6000 tokens → Hardware crying quietly in the corner: yes so is 3 tps actually usable? For real time back and forth chat? Not ideal. You're not having a fluid conversation at 3 tps. but slow ≠ useless. And this is where it gets genuinely interesting. think about how senior devs actually work in a real team. But when something is architectural, deeply complex, or needs serious reasoning? they walk down the hall and escalate to the senior. That's exactly the local AI agent architecture this unlocks: → Fast orchestrator model (Gemma 4 26B MoE at 25+ tps) handles routing, simple queries, tool calls, memory. The junior dev. → Gemma 4 31B dense is the senior, called only when the fast model genuinely hits a wall. Hard multi step reasoning. Complex code generation. Deep architectural decisions. The agentic loop stays fast. Only the hard hops touch the 31B. That's a legitimate production grade local AI architecture on a budget hardware. (requires 2 8gb gpus) other workflows where 3 tps is completely fine: - overnight batch jobs. summarize documents, extract structured data, review code. Fire it off. Sleep. wake up to results. - One shot deep reasoning - Silent code audit loops, you write and test, the 31B reviews diffs and flags issues in the background between your sprints - Any workflow where output quality > output speed A few weeks ago, nobody was running a 30B+ dense model on a single consumer GPU with 8 GB VRAM. At all. Now we're doing it on an Intel i7-H gaming laptop with a NVIDIA RTX 4060, thanks to llama.cpp + QAT quants + MTP speculative drafting. Google DeepMind said the Gemma 4 31B targets "consumer GPUs and workstations." They were not exaggerating. The hardware bar to run serious frontier class models locally keeps dropping. the tools are here. the models are here. you just have to be willing to abuse your laptop a little. what workflows would you actually run on a local 3 tps 31B dense model? genuinely curious. drop it below.

Alok

63,095 views • 1 month ago

gemma-4-12B-agentic-fable5-composer2.5 V2 is out. the agentic upgrade to the model trained on Fable 5's reasoning. Running it now with TurboQuant llama.cpp on a single RTX 4060( 8 GB VRAM) at 30 tokens/second with full 25000 context and reasoning: # The benchmarks v2 is built for coding + agentic work. writing code, running commands, using tools, debugging, multi step technical tasks. The clearest signal is tau2 bench telecom, an agentic tool use benchmark whose diagnose → fix → verify loop mirrors real terminal/debugging work: tau2 bench telecom numbers: base Gemma 4 12B: ~15% this finetune: ~55%. (Self reported) thats a huge jump # TheTom/llama-cpp-turboquant flags: llama-server.exe -m gemma4-v2-Q4_K_M.gguf -ngl 99 -c 25000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 Flag breakdown: -ngl 99 → full GPU offload -c 25000 → 25K context --cache-type-k q8_0 --cache-type-v turbo3 → mixed-precision KV cache — K at 8-bit, V at ~3-bit via TurboQuant (Walsh Hadamard rotated polar quant, Google's own KV-compression research). Not even merged into mainline llama.cpp. running it off a fork. No API. No cloud. Just llama.cpp. well, a fork of it and any 6gb+ GPU. If you tried yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF, check this out and share your experience with the models

gemma-4-12B-agentic-fable5-composer2.5 V2 is out. the agentic upgrade to the model trained on Fable 5's reasoning. Running it now with TurboQuant llama.cpp on a single RTX 4060( 8 GB VRAM) at 30 tokens/second with full 25000 context and reasoning: # The benchmarks v2 is built for coding + agentic work. writing code, running commands, using tools, debugging, multi step technical tasks. The clearest signal is tau2 bench telecom, an agentic tool use benchmark whose diagnose → fix → verify loop mirrors real terminal/debugging work: tau2 bench telecom numbers: base Gemma 4 12B: ~15% this finetune: ~55%. (Self reported) thats a huge jump # TheTom/llama-cpp-turboquant flags: llama-server.exe -m gemma4-v2-Q4_K_M.gguf -ngl 99 -c 25000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 Flag breakdown: -ngl 99 → full GPU offload -c 25000 → 25K context --cache-type-k q8_0 --cache-type-v turbo3 → mixed-precision KV cache — K at 8-bit, V at ~3-bit via TurboQuant (Walsh Hadamard rotated polar quant, Google's own KV-compression research). Not even merged into mainline llama.cpp. running it off a fork. No API. No cloud. Just llama.cpp. well, a fork of it and any 6gb+ GPU. If you tried yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF, check this out and share your experience with the models

Alok

144,654 views • 27 days ago

90% of "AI developers" just download pre packaged GGUF files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.

Alok

60,378 views • 8 days ago

single RTX 3090. 24 GB VRAM. Qwen3.5-35B-A3B. 4-bit quant, 113 tokens per second at full 262K context harnessing Claude Code locally with no API, no subscription, no proxy. told it what it is. 30 Mamba2 layers, 10 attention, 256 experts, 8 active per token. said "build something that shows off what you can do." it visualized its own architecture. interactive. tokens flowing through layers. 256 experts lighting up on routing. served in the browser from the same GPU running inference. single prompt. then i said level up. 3D. Three.js. separate files. flythrough camera. clickable layers. it planned first, scaffolded 6 files, hit one API bug, fixed it itself, then optimized for smooth framerate. two iterations to a working 3D neural network explorer. llama.cpp just merged a native Anthropic endpoint. Claude Code points at localhost. the whole setup is two commands. no LiteLLM. no proxy config. the open source models coming out of china right now are genuinely changing what's possible on consumer hardware. respect to the Qwen team. this is acceleration.

single RTX 3090. 24 GB VRAM. Qwen3.5-35B-A3B. 4-bit quant, 113 tokens per second at full 262K context harnessing Claude Code locally with no API, no subscription, no proxy. told it what it is. 30 Mamba2 layers, 10 attention, 256 experts, 8 active per token. said "build something that shows off what you can do." it visualized its own architecture. interactive. tokens flowing through layers. 256 experts lighting up on routing. served in the browser from the same GPU running inference. single prompt. then i said level up. 3D. Three.js. separate files. flythrough camera. clickable layers. it planned first, scaffolded 6 files, hit one API bug, fixed it itself, then optimized for smooth framerate. two iterations to a working 3D neural network explorer. llama.cpp just merged a native Anthropic endpoint. Claude Code points at localhost. the whole setup is two commands. no LiteLLM. no proxy config. the open source models coming out of china right now are genuinely changing what's possible on consumer hardware. respect to the Qwen team. this is acceleration.

Sudo su

110,206 views • 4 months ago

INTRODUCING OCBTW: THE FIRST PANDA-BACKED ASSET A FIRST-OF-ITS-KIND 2-WAY NFT NFT SWAP We just deployed a smart contract on Bitcoin that allows you to mint "OCBTW", a limited edition generative art collection by tclow.sats, solely by swapping an Alkane Pandas ⬢ OCBTW has a supply of 200 unique pieces and is inspired by Oyl | Building Alkanes's signature hexagon logo that defines all native Alkane assets (e.g., $DIESEL). It is 100% on-chain generative art using three.js code via HTML ⬢ OCBTW can only be minted by swapping a Panda using the 2:70104 smart contract. After 200 swaps have been completed, on a first-come-first-served basis, the mint will conclude. However, OCBTW can be swapped back to a Panda at any time, freeing up supply for another Panda holder to collect a OCBTW piece from the contract. ⬢ OCBTW is thus backed entirely by Pandas, meaning each piece will never be worth less than a Panda. This is the first time on Bitcoin that an NFT is minted with another NFT. This may be the first time this has ever been done on any chain. ⬢ OCBTW also effectively locks up up to 200 Pandas for perpetuity. Just like AP-69, this swap contract has no withdrawal function. The only way to get Pandas out of the contract is to swap your OCBTW back to a Panda. This operates on a last-in, first-out (LIFO) basis. ⬢ OCBTW can be minted by calling the 2:70104 contract using opcode 42 and including a Panda in the transaction, either by using or You can only mint 1 OCBTW per transaction. Rarity of Pandas has no effect on what OCBTW mint you will receive. ⬢ OCBTW can be viewed natively in browser on iDclub 💥 Building Alkanes at the following link: Please be patient after minting for their indexer to update after blocks clear. Please also note that the Ordiscan Alkanes indexer is currently down. ⬢ OCBTW is purely art. Art on Bitcoin. Forever.

Alkane Pandas

22,591 views • 10 months ago

[LSTM] by Hand ✍️ LSTMs have been the most effective architecture to process long sequences of data, until our world was taken over by the Transformers. LSTMs belong to the broader family of recurrent neural network (RNNs) that process data sequentially in a recurrent manner. Transformers, on the other hand, abandon recurrence and use self-attention instead to process data concurrently in parallel. Recently, there is renewed interest in recurrence as people realized self-attention doesn’t scale to extremely long sequences, like hundreds of thousands of tokens. Mamba is a good example to bring back recurrence. All of a sudden, it is cool to study LSTMs. How do LSTMs work? [1] Given ↳ 🟨 Input sequence X1, X2, X3 (d = 3) ↳ 🟩 Hidden state h (d = 2) ↳ 🟦 Memory C (d = 2) ↳ Weight matrices Wf, Wc, Wi, Wo Process t = 1 [2] Initialize ↳ Randomly set the previous hidden state h0 to [1, 1] and memory cells C0 to [0.3, -0.5] [3] Linear Transform ↳ Multiply the four weight matrices with the concatenation of current input (X1) and the previous hidden state (h0). ↳ The results are feature values, each is a linear combination of the current input and hidden state. [4] Non-linear Transform ↳ Apply sigmoid σ to obtain gate values (between 0 and 1). • Forget gate (f1): [-4, -6] → [0, 0] • Input gate (i1): [6, 4] → [1, 1] • Output gate (o1): [4, -5] → [1, 0] ↳ Apply tanh to obtain candidate memory values (between -1 and 1) • Candidate memory (C’1): [1, -6] → [0.8, -1] [5] Update Memory ↳ Forget (C0 .* f1): Element-wise multiply the current memory with forget gate values. ↳ Input (C’1 .* o1): Element-wise multiply the “candidate” memory with input gate values. ↳ Update the memory to C1 by adding the two terms above: C0 .* f1 + C’1 .* o1 = C1 [6] Candiate Output ↳ Apply tanh to the new memory C1 to obtain candidate output o’1. [0.8, -1] → [0.7, -0.8] [7] Update Hidden State ↳ Output (o’1 .* o1 → h1): Element-wise multiply the candidate output with the output gate. ↳ The result is updated hidden state h1 ↳ Also, it is the first output. Process t = 2 [8] Initialize ↳ Copy previous hidden state h1 and memory C1 [9] Linear Transform ↳ Repeat [3] [10] Update Memory (C2) ↳ Repeat [4] and [5] [11] Update Hidden State (h2) ↳ Repeat [6] and [7] Process t = 3 [12] Initialize ↳ Copy previous hidden state h2 and memory C2 [13] Linear Transform ↳ Repeat [3] [14] Update Memory (C3) ↳ Repeat [4] and [5] [15] Update Hidden State (h3) ↳ Repeat [6] and [7]

[LSTM] by Hand ✍️ LSTMs have been the most effective architecture to process long sequences of data, until our world was taken over by the Transformers. LSTMs belong to the broader family of recurrent neural network (RNNs) that process data sequentially in a recurrent manner. Transformers, on the other hand, abandon recurrence and use self-attention instead to process data concurrently in parallel. Recently, there is renewed interest in recurrence as people realized self-attention doesn’t scale to extremely long sequences, like hundreds of thousands of tokens. Mamba is a good example to bring back recurrence. All of a sudden, it is cool to study LSTMs. How do LSTMs work? [1] Given ↳ 🟨 Input sequence X1, X2, X3 (d = 3) ↳ 🟩 Hidden state h (d = 2) ↳ 🟦 Memory C (d = 2) ↳ Weight matrices Wf, Wc, Wi, Wo Process t = 1 [2] Initialize ↳ Randomly set the previous hidden state h0 to [1, 1] and memory cells C0 to [0.3, -0.5] [3] Linear Transform ↳ Multiply the four weight matrices with the concatenation of current input (X1) and the previous hidden state (h0). ↳ The results are feature values, each is a linear combination of the current input and hidden state. [4] Non-linear Transform ↳ Apply sigmoid σ to obtain gate values (between 0 and 1). • Forget gate (f1): [-4, -6] → [0, 0] • Input gate (i1): [6, 4] → [1, 1] • Output gate (o1): [4, -5] → [1, 0] ↳ Apply tanh to obtain candidate memory values (between -1 and 1) • Candidate memory (C’1): [1, -6] → [0.8, -1] [5] Update Memory ↳ Forget (C0 .* f1): Element-wise multiply the current memory with forget gate values. ↳ Input (C’1 .* o1): Element-wise multiply the “candidate” memory with input gate values. ↳ Update the memory to C1 by adding the two terms above: C0 .* f1 + C’1 .* o1 = C1 [6] Candiate Output ↳ Apply tanh to the new memory C1 to obtain candidate output o’1. [0.8, -1] → [0.7, -0.8] [7] Update Hidden State ↳ Output (o’1 .* o1 → h1): Element-wise multiply the candidate output with the output gate. ↳ The result is updated hidden state h1 ↳ Also, it is the first output. Process t = 2 [8] Initialize ↳ Copy previous hidden state h1 and memory C1 [9] Linear Transform ↳ Repeat [3] [10] Update Memory (C2) ↳ Repeat [4] and [5] [11] Update Hidden State (h2) ↳ Repeat [6] and [7] Process t = 3 [12] Initialize ↳ Copy previous hidden state h2 and memory C2 [13] Linear Transform ↳ Repeat [3] [14] Update Memory (C3) ↳ Repeat [4] and [5] [15] Update Hidden State (h3) ↳ Repeat [6] and [7]

Tom Yeh

72,891 views • 2 years ago

BREAKING: LLMs just learned to COMPUTE for real, it's mean NO MORE GUESSING math. Chinese college kid Guo Hanjiang vibe-coded MiroFish in 10 days (23k+ GitHub stars, $4.1M from Shanda in 24h) - the AI swarm simulator that’s already printing. ByteDance (VolcEngine) dropped the nuclear upgrade: OpenViking - structured viking:// filesystem memory (L0 ultra-summary -> L2 full details) - agents now run 100+ steps with zero amnesia or hallucinations, 11.6k stars and climbing. Now this just dropped and the entire AI timeline is shaking. Startup Percepta embedded a full WASM virtual machine directly into Transformer weights. No more external Python sandboxes. No more hallucinations in exact tasks. The model streams raw machine code at 30,000+ tokens/sec on CPU, executes millions of steps, and solves the world’s hardest Sudoku via real backtracking + constraint propagation - 100% accurate, zero bullshit. They killed the Attention Bottleneck with Exponentially Fast Attention (HullKVCache + 2D heads + convex hull queries in log time). What used to die at 1k steps now flies. This is the bridge: System 1 intuition (normal LLMs) + System 2 deterministic logic (native code execution) in ONE brain. Agents won’t need tools anymore. Heavy simulations will run inside the weights. Check out: Now put it all together: MiroFish swarms + OpenViking infinite memory + Percepta native flawless compute = agents that can hardcore simulate millions of future scenarios, run perfect logic loops for days, and predict events/markets/reality with god-tier accuracy. No drift. No bullshit. Just pure foresight. This combo will change everything, imo. The era of predictive super-agents that actually print the future is here. We’re watching this one closely. Save this combo.

BREAKING: LLMs just learned to COMPUTE for real, it's mean NO MORE GUESSING math. Chinese college kid Guo Hanjiang vibe-coded MiroFish in 10 days (23k+ GitHub stars, $4.1M from Shanda in 24h) - the AI swarm simulator that’s already printing. ByteDance (VolcEngine) dropped the nuclear upgrade: OpenViking - structured viking:// filesystem memory (L0 ultra-summary -> L2 full details) - agents now run 100+ steps with zero amnesia or hallucinations, 11.6k stars and climbing. Now this just dropped and the entire AI timeline is shaking. Startup Percepta embedded a full WASM virtual machine directly into Transformer weights. No more external Python sandboxes. No more hallucinations in exact tasks. The model streams raw machine code at 30,000+ tokens/sec on CPU, executes millions of steps, and solves the world’s hardest Sudoku via real backtracking + constraint propagation - 100% accurate, zero bullshit. They killed the Attention Bottleneck with Exponentially Fast Attention (HullKVCache + 2D heads + convex hull queries in log time). What used to die at 1k steps now flies. This is the bridge: System 1 intuition (normal LLMs) + System 2 deterministic logic (native code execution) in ONE brain. Agents won’t need tools anymore. Heavy simulations will run inside the weights. Check out: Now put it all together: MiroFish swarms + OpenViking infinite memory + Percepta native flawless compute = agents that can hardcore simulate millions of future scenarios, run perfect logic loops for days, and predict events/markets/reality with god-tier accuracy. No drift. No bullshit. Just pure foresight. This combo will change everything, imo. The era of predictive super-agents that actually print the future is here. We’re watching this one closely. Save this combo.

slash1s

156,699 views • 4 months ago

Run Gemma 4 26b MTP on 8 GB VRAM GPUs at 25+ tokens/second. Flags included! local llm space is moving at terminal velocity. only 3 days ago google released gemma 4 26b a4b qat quants. more efficient than before, ran on 8gb vram at 20 tok/sec. and now just a few hours ago, mainline llama.cpp merged a massive update and we just shattered our own record. decode throughput went 25-40% up on the same 8 GB VRAM setup! Before MTP: 20 tps -> After MTP: 28 tps! llama.cpp just officially merged PR #23398 ("add Gemma4 MTP"), bringing native Multi-Token Prediction (MTP) support to Gemma 4 models. By running speculative drafting on the same 8GB VRAM RTX 4060 setup, my decode throughput on a 64k context instantly leaped to a blistering 25–27 tokens/sec thats 25-30% increase with the same hardware. Here is the architectural catch you need to know: Unlike the Qwen 3.5 and 3.6 series, which bake the MTP heads directly into the base GGUF, the Gemma 4 MTP head is not built in. You must download a separate, specialized MTP drafter GGUF (the assistant model) to act as the speculator. (I've dropped the download link in the replies). copy and try the exact flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.7 --spec-draft-model gemma-4-26b-A4B-it-assistant-Q4_0.gguf -c 64000 -v n-max 4 and p-min 0.7 is also worth checking out. benchmark on your setup and workflow. if you have a single 8 gb vram nvidia rtx 4060, 3060, 3070, 2080, 2070, grab the MTP drafter GGUF link in the comments and try it yourself. Check it out even if you have asmaller or a larger gpu, such as a single rtx 3090, 4090, 3060, 2060. MTP works for all gemma 4 sizes such as gemma 4 12b, gemma 4 31b etc. but remember to grab the correct mtp draft assistant models respectively. what are you benchmarking today

Run Gemma 4 26b MTP on 8 GB VRAM GPUs at 25+ tokens/second. Flags included! local llm space is moving at terminal velocity. only 3 days ago google released gemma 4 26b a4b qat quants. more efficient than before, ran on 8gb vram at 20 tok/sec. and now just a few hours ago, mainline llama.cpp merged a massive update and we just shattered our own record. decode throughput went 25-40% up on the same 8 GB VRAM setup! Before MTP: 20 tps -> After MTP: 28 tps! llama.cpp just officially merged PR #23398 ("add Gemma4 MTP"), bringing native Multi-Token Prediction (MTP) support to Gemma 4 models. By running speculative drafting on the same 8GB VRAM RTX 4060 setup, my decode throughput on a 64k context instantly leaped to a blistering 25–27 tokens/sec thats 25-30% increase with the same hardware. Here is the architectural catch you need to know: Unlike the Qwen 3.5 and 3.6 series, which bake the MTP heads directly into the base GGUF, the Gemma 4 MTP head is not built in. You must download a separate, specialized MTP drafter GGUF (the assistant model) to act as the speculator. (I've dropped the download link in the replies). copy and try the exact flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.7 --spec-draft-model gemma-4-26b-A4B-it-assistant-Q4_0.gguf -c 64000 -v n-max 4 and p-min 0.7 is also worth checking out. benchmark on your setup and workflow. if you have a single 8 gb vram nvidia rtx 4060, 3060, 3070, 2080, 2070, grab the MTP drafter GGUF link in the comments and try it yourself. Check it out even if you have asmaller or a larger gpu, such as a single rtx 3090, 4090, 3060, 2060. MTP works for all gemma 4 sizes such as gemma 4 12b, gemma 4 31b etc. but remember to grab the correct mtp draft assistant models respectively. what are you benchmarking today

Alok

200,913 views • 1 month ago

Do you want to own part of a AAA game? I know, you hear it all the time. “Triple A game”, you go to play it, it’s crap. This is different, and it’s only possible with Sonic (Sonic) speed, transaction cost, and of-course FeeM. A game that includes talent from Kojima, Ubisoft, EA Sports, Gameloft & more with advisors from NVIDIA. A game that you’ll be able to play on mobile, desktop, and then Xbox and PlayStation (yes really)! YES! A PRETTY BIG DEAL! Before I tell you about the sale, let me at least tell you about this game (being a massive gamer nerd, this excited me), so…. Introducing Animera (Search for Animera): • Fast-paced skill-based PvP in the Nubera galaxy • Compete in real-time space battles for real rewards It will be powered with $STRIKE: • Compete2Earn: win matches, earn tokens • Play2Burn: 5% of $STRIKE used in matches gets burned Oh, and with 8.75% of all game revenue will be used to buy & burn $SWPx, so the SwapX (SwapX) community owns a real stake in this AAA title. Absolutely insane. > Now let me tell you about its beta run quickly: • 16K+ beta signups • 500+ players added weekly • 7.5K+ matches already played • Launching to 500K+ mobile users via Nomina Games > How can you own a piece of Animera? June 5th at 2pm EDT the sale will go live on SwapX, it will go in three phases each lasting 12 hours or until sold out: PHASE 1️⃣: xNFT Holders Early access with exclusive perks and bonuses. These are for xNFT holders only you can get these here on paintswap PHASE 2️⃣ Whitelisted Communities These will be whitelisted from Creo Engine, SFA AGC, derp, and GOGLZ | SONIC 🥽💥. PHASE 3️⃣ Public Round Any remaining allocation will open to the public - only if Phases 1 & 2 don’t sell out. > What is the raise? Token Price & Allocation: • Token: $STRIKE • Currency: USDC • Total tokens for sale: 101.75M Unlock structure: • 50% unlocked at TGE • Remaining 50% claimable in 30 days • Raise cap: Max $100,000 per user, capped at $10,000 per xNFT • Purchase window priority: xNFT holders get early access (see above)! Transparency is key: Why I love working with the team is because transparency is crucial, so I’m going to tell you about its tokenomics, seed, and fully diluted valuation here: Token Symbol: STRIKE Total Supply: 370,000,000 Initial FDV: $1.48M Total Raise: $950,160 Total Initial Unlock: 112,947,501 STRIKE Initial Market Cap (excluding liquidity): $303,790 Token Allocation: • Seed Round: 59.2M tokens (16% allocation), with a 1-month cliff and linear vesting over 9 months. • Private Round: 94.35M tokens (25.5% allocation), with a 1-month cliff and 6-month vesting period. • Crowdsale: 10.75M tokens (2.91% allocation), unlocked 50% at TGE. • xNFT Holders: 10M tokens (2.7% allocation), with a 1-month cliff. • Liquidity: 37M tokens (10% allocation), with no lock or vesting. • Team: 18.5M tokens (5% allocation), with a 6-month cliff and 12-month vesting. • Rewards: 28.6M tokens (8% allocation), vested over 18 months. • Product Growth: 19.6M tokens (5.3% allocation), vested over 24 months. Token Offering: • Seed Round: Priced at $0.0033 per token, raising $195,360 by selling 59.2M tokens. 10% unlocks at TGE, with a 1-month cliff and 9-month vesting. The initial market cap from seed unlock is $234,127. • Private Round: Priced at $0.0037 per token, raising $349,095 for 94.35M tokens. 15% unlocks at TGE, with a 1-month cliff and 6-month vesting. Initial market cap contribution is $262,508. • Crowdsale: Priced at $0.0040 per token, raising $407,000 by selling 10.75M tokens. 50% unlocks at TGE, with no cliff or vesting. Adds $283,790 to the initial market cap. It’s important you had the full information at hand so you can decide whether or not you’d like to participate. I will be, because it’s a low FDV and it looks great. This is not financial advice, I’m helping the team out. Below is real gameplay: Further details: 👇

Do you want to own part of a AAA game? I know, you hear it all the time. “Triple A game”, you go to play it, it’s crap. This is different, and it’s only possible with Sonic (Sonic) speed, transaction cost, and of-course FeeM. A game that includes talent from Kojima, Ubisoft, EA Sports, Gameloft & more with advisors from NVIDIA. A game that you’ll be able to play on mobile, desktop, and then Xbox and PlayStation (yes really)! YES! A PRETTY BIG DEAL! Before I tell you about the sale, let me at least tell you about this game (being a massive gamer nerd, this excited me), so…. Introducing Animera (Search for Animera): • Fast-paced skill-based PvP in the Nubera galaxy • Compete in real-time space battles for real rewards It will be powered with $STRIKE: • Compete2Earn: win matches, earn tokens • Play2Burn: 5% of $STRIKE used in matches gets burned Oh, and with 8.75% of all game revenue will be used to buy & burn $SWPx, so the SwapX (SwapX) community owns a real stake in this AAA title. Absolutely insane. > Now let me tell you about its beta run quickly: • 16K+ beta signups • 500+ players added weekly • 7.5K+ matches already played • Launching to 500K+ mobile users via Nomina Games > How can you own a piece of Animera? June 5th at 2pm EDT the sale will go live on SwapX, it will go in three phases each lasting 12 hours or until sold out: PHASE 1️⃣: xNFT Holders Early access with exclusive perks and bonuses. These are for xNFT holders only you can get these here on paintswap PHASE 2️⃣ Whitelisted Communities These will be whitelisted from Creo Engine, SFA AGC, derp, and GOGLZ | SONIC 🥽💥. PHASE 3️⃣ Public Round Any remaining allocation will open to the public - only if Phases 1 & 2 don’t sell out. > What is the raise? Token Price & Allocation: • Token: $STRIKE • Currency: USDC • Total tokens for sale: 101.75M Unlock structure: • 50% unlocked at TGE • Remaining 50% claimable in 30 days • Raise cap: Max $100,000 per user, capped at $10,000 per xNFT • Purchase window priority: xNFT holders get early access (see above)! Transparency is key: Why I love working with the team is because transparency is crucial, so I’m going to tell you about its tokenomics, seed, and fully diluted valuation here: Token Symbol: STRIKE Total Supply: 370,000,000 Initial FDV: $1.48M Total Raise: $950,160 Total Initial Unlock: 112,947,501 STRIKE Initial Market Cap (excluding liquidity): $303,790 Token Allocation: • Seed Round: 59.2M tokens (16% allocation), with a 1-month cliff and linear vesting over 9 months. • Private Round: 94.35M tokens (25.5% allocation), with a 1-month cliff and 6-month vesting period. • Crowdsale: 10.75M tokens (2.91% allocation), unlocked 50% at TGE. • xNFT Holders: 10M tokens (2.7% allocation), with a 1-month cliff. • Liquidity: 37M tokens (10% allocation), with no lock or vesting. • Team: 18.5M tokens (5% allocation), with a 6-month cliff and 12-month vesting. • Rewards: 28.6M tokens (8% allocation), vested over 18 months. • Product Growth: 19.6M tokens (5.3% allocation), vested over 24 months. Token Offering: • Seed Round: Priced at $0.0033 per token, raising $195,360 by selling 59.2M tokens. 10% unlocks at TGE, with a 1-month cliff and 9-month vesting. The initial market cap from seed unlock is $234,127. • Private Round: Priced at $0.0037 per token, raising $349,095 for 94.35M tokens. 15% unlocks at TGE, with a 1-month cliff and 6-month vesting. Initial market cap contribution is $262,508. • Crowdsale: Priced at $0.0040 per token, raising $407,000 by selling 10.75M tokens. 50% unlocks at TGE, with no cliff or vesting. Adds $283,790 to the initial market cap. It’s important you had the full information at hand so you can decide whether or not you’d like to participate. I will be, because it’s a low FDV and it looks great. This is not financial advice, I’m helping the team out. Below is real gameplay: Further details: 👇

hoeem

21,634 views • 1 year ago