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.

Microsoft just changed the game 🤯 They've open-sourced bitnet.cpp, a 1-bit LLM inference framework. It let's you run 100B parameter models on your local CPU without GPUs. - 6.17x faster inference - 82.2% less energy on CPUs 100% Open Source.

Oliver Prompts

22,589 subscribers

114,930 views • 13 days ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Biologists use specialized open-source models for tasks like modeling the structure of molecular systems, designing drug-like molecules, and predicting the effects of genetic mutations. But these models are often expensive to run, potentially limiting their impact. In our latest Science Blog, we share how Claude was able to optimize inference for more than 30 open-source models, making them 4x faster on average, partly by writing custom software for GPUs. We’re open sourcing all of the optimization code. Read more:

Biologists use specialized open-source models for tasks like modeling the structure of molecular systems, designing drug-like molecules, and predicting the effects of genetic mutations. But these models are often expensive to run, potentially limiting their impact. In our latest Science Blog, we share how Claude was able to optimize inference for more than 30 open-source models, making them 4x faster on average, partly by writing custom software for GPUs. We’re open sourcing all of the optimization code. Read more:

Anthropic

633,322 views • 1 month ago

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.

Cline Desktop just launched. An open-source workspace for open-weight models 🤯 > Import tasks from other coding agents > Run agents in parallel > Schedule tasks to run on their own Free models built in: DeepSeek V4 Flash, GLM 5.3 Flash, Laguna S 2.1. I had early access and I can assure you it feels incredible. Pick your model and provider, and run it. 100% open source.

Alvaro Cintas

15,934 views • 1 month ago

someone just open-sourced their own neuro-sama. and it might be better than the original. it's called airi. a fully autonomous ai companion that talks to you in real time, plays minecraft and factorio with you, chats on discord and telegram, and has a live2d/vrm avatar body. runs entirely on your machine. → real-time voice conversations, speech recognition → animated avatar with auto-blink, eye tracking, idle animations → persistent memory across sessions → local inference via webgpu, no api calls needed supports 30+ llm providers, openai, claude, gemini, deepseek, ollama, groq, mistral, xai, local models. swap the brain with a config change. runs on native cuda and apple metal for real gpu acceleration. 17.5k stars. 101 contributors. 46 releases. 100% free. open source.

Oliver Prompts

289,874 views • 2 months ago

🔥 BREAKING: Open source just leveled up AI agents Eigent gives you a fully local, customizable AI workforce....built to run on your laptop. → No vendor lock-in → No cloud dependency → 100% open source Just fast, private, parallel agents you control (Here's how):👇

🔥 BREAKING: Open source just leveled up AI agents Eigent gives you a fully local, customizable AI workforce....built to run on your laptop. → No vendor lock-in → No cloud dependency → 100% open source Just fast, private, parallel agents you control (Here's how):👇

Shruti

63,497 views • 1 year ago

world models have their comfyui now. introducing alakazam studio, the first local, open source UI for world models. •⁠ ⁠sentence goes in => you edit the state graph => play •⁠ ⁠on a live model, yours, running in your browser •⁠ ⁠⁠apache-2.0, fully open source fork it and point it at your model 👇

world models have their comfyui now. introducing alakazam studio, the first local, open source UI for world models. •⁠ ⁠sentence goes in => you edit the state graph => play •⁠ ⁠on a live model, yours, running in your browser •⁠ ⁠⁠apache-2.0, fully open source fork it and point it at your model 👇

hugo

26,438 views • 2 months ago

They were building in stealth for 2 years, I was building in stealth for 2 hours… Happy to open source Qwen-2.5-1B-RLCD, 5x faster on-device inference for JSON workloads that need to be type-safe. ⚡️Demo below on a M4 MacBook⚡️ every LLM has the ability to efficiently batch inference every key of a JSON at the same time and generate probabilities from a set of possible categories. No new training required, but it’s easy to optimize if you need! On hugging face now!

They were building in stealth for 2 years, I was building in stealth for 2 hours… Happy to open source Qwen-2.5-1B-RLCD, 5x faster on-device inference for JSON workloads that need to be type-safe. ⚡️Demo below on a M4 MacBook⚡️ every LLM has the ability to efficiently batch inference every key of a JSON at the same time and generate probabilities from a set of possible categories. No new training required, but it’s easy to optimize if you need! On hugging face now!

Harsha Gundala

1,299,086 views • 1 month ago

someone just open-sourced their own neuro-sama. and it might be better than the original. it's called airi. a fully autonomous ai companion that speaks with you in real time, joins you in minecraft and factorio, chats through discord and telegram, and comes with a live2d/vrm avatar. runs entirely on your machine. → real-time voice chat and speech recognition → animated avatar with automatic blinking, eye tracking, and idle movements → persistent memory between sessions → local inference through webgpu, no api calls required supports 30+ llm providers, including openai, claude, gemini, deepseek, ollama, groq, mistral, xai, and local models. switch the brain with a config change. uses native cuda and apple metal for real gpu acceleration. 17.5k stars. 101 contributors. 46 releases. completely free. open source.

Simplifying AI

195,338 views • 26 days ago

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

Superman

104,663 views • 3 months ago

Depth Anything 3 now runs as pure C++/ggml (ggml) . No Python, no PyTorch, no CUDA toolkit at inference, just one self-contained GGUF. It's faster than PyTorch on CPU! and ties speed on GPU. The CPU win came from the last place..I'd have looked. Quantized GGUF on Hugging Face🤗 Shout out to Georgi Gerganov for ggml (we are building a ggml-world!❤️) and to ByteDance Open Source and Depth Anything 3 authors Bingyi Kang Jun Hao Liew Donny Y. Chen !

Depth Anything 3 now runs as pure C++/ggml (ggml) . No Python, no PyTorch, no CUDA toolkit at inference, just one self-contained GGUF. It's faster than PyTorch on CPU! and ties speed on GPU. The CPU win came from the last place..I'd have looked. Quantized GGUF on Hugging Face🤗 Shout out to Georgi Gerganov for ggml (we are building a ggml-world!❤️) and to ByteDance Open Source and Depth Anything 3 authors Bingyi Kang Jun Hao Liew Donny Y. Chen !

Ettore Di Giacinto

34,915 views • 4 months ago

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Qwen has just released a model on par with GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details below

Paul Couvert

504,333 views • 1 year ago

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:

Stability AI

95,366 views • 1 year ago

Turn any open LLM into a Jev-style model: Researchers just open-sourced AnyJev, a Python library that extracts typed choices, yes/no judgments, scores, and probabilities from causal LLMs. Beyond its raw baseline, AnyJev offers three levels depending on how much labeled data and calibration you need: - L0 requires no labels. It rotates the answer options to reduce position bias, but its probabilities remain uncalibrated. - L1 uses 100-500 labeled examples per question to calibrate those probabilities through temperature scaling. It improves confidence estimates without changing the answer ranking. - L2 uses 100-300 labels to fit a closed-form head on an intermediate hidden state. It leaves model weights untouched and can stop inference before the full forward pass completes. The main constraint is model access. AnyJev requires access to logits or hidden states, so it is built for open models. L2 heads are also specific to a model and question. It is compatible with several open causal LLMs. Repo: (don't forget to star it ⭐ ) If you want to dive deeper, I also wrote about a similar mechanism in a hands-on guide. It covers building a Jev-style decision path with open models, entirely locally. Read it below.

Turn any open LLM into a Jev-style model: Researchers just open-sourced AnyJev, a Python library that extracts typed choices, yes/no judgments, scores, and probabilities from causal LLMs. Beyond its raw baseline, AnyJev offers three levels depending on how much labeled data and calibration you need: - L0 requires no labels. It rotates the answer options to reduce position bias, but its probabilities remain uncalibrated. - L1 uses 100-500 labeled examples per question to calibrate those probabilities through temperature scaling. It improves confidence estimates without changing the answer ranking. - L2 uses 100-300 labels to fit a closed-form head on an intermediate hidden state. It leaves model weights untouched and can stop inference before the full forward pass completes. The main constraint is model access. AnyJev requires access to logits or hidden states, so it is built for open models. L2 heads are also specific to a model and question. It is compatible with several open causal LLMs. Repo: (don't forget to star it ⭐ ) If you want to dive deeper, I also wrote about a similar mechanism in a hands-on guide. It covers building a Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

56,140 views • 28 days ago

Your PC can now run an entire AI studio for free. Locally Uncensored puts chat, image generation, video generation, and a coding agent in one desktop app for Windows and Linux. - Chat with local models and your own documents - Generate images and videos on your GPU - Write code and review changes before applying them - Run agents with tools and MCP connections Install it, pick a model, and start. It shows which models fit your hardware before you download. No Docker. No terminal. No cloud required for the local workflows. 100% Free. Open Source.

Your PC can now run an entire AI studio for free. Locally Uncensored puts chat, image generation, video generation, and a coding agent in one desktop app for Windows and Linux. - Chat with local models and your own documents - Generate images and videos on your GPU - Write code and review changes before applying them - Run agents with tools and MCP connections Install it, pick a model, and start. It shows which models fit your hardware before you download. No Docker. No terminal. No cloud required for the local workflows. 100% Free. Open Source.

Oliver Prompts

21,751 views • 17 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

62,631 views • 3 months ago

Our open-source RAG app, Verba, can now run Ollama models locally to embed documents into Weaviate and generate answers without your data leaving your device! I tested it with Llama3, and it works great + super quickly on my M2; In this recording, I'm doing a little Verba-ception, asking Verba what Verba is 🤤 You can also use open-source models like Mistral, Claude, or your own custom LLMs. This will make doing RAG with sensitive data possible since you won't depend on APIs anymore. Looking forward to everyone trying it out 🤗 Update's coming next week!

Our open-source RAG app, Verba, can now run Ollama models locally to embed documents into Weaviate and generate answers without your data leaving your device! I tested it with Llama3, and it works great + super quickly on my M2; In this recording, I'm doing a little Verba-ception, asking Verba what Verba is 🤤 You can also use open-source models like Mistral, Claude, or your own custom LLMs. This will make doing RAG with sensitive data possible since you won't depend on APIs anymore. Looking forward to everyone trying it out 🤗 Update's coming next week!

Edward

125,596 views • 2 years ago

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

yazin

293,633 views • 7 months ago

🚨 Alibaba just open sourced a GUI agent that lives inside your webpage and controls it with natural language. It's called Page Agent and it's not a browser extension. It's pure JavaScript no Python, no Puppeteer, no headless browser, no screenshots. Just one script tag and your web app understands natural language. Here's what it actually does: → Embed it with a single tag or npm install → Control any web interface with plain English commands → Text-based DOM manipulation no OCR, no vision models needed → Bring your own LLM (GPT, Claude, Qwen, anything) → Ships a built-in UI with human-in-the-loop support → Turn 20-click ERP/CRM workflows into one sentence → Optional Chrome extension for multi-tab agent tasks → Works on any web app SaaS, admin panels, internal tools Companies are charging $30/month for AI copilots built on this exact idea. This is 3 lines of code. Your users. Your interface. The AI copilot layer for every web app just got open sourced. 1.6K stars. 100% Open Source. (Link in the comments)

🚨 Alibaba just open sourced a GUI agent that lives inside your webpage and controls it with natural language. It's called Page Agent and it's not a browser extension. It's pure JavaScript no Python, no Puppeteer, no headless browser, no screenshots. Just one script tag and your web app understands natural language. Here's what it actually does: → Embed it with a single tag or npm install → Control any web interface with plain English commands → Text-based DOM manipulation no OCR, no vision models needed → Bring your own LLM (GPT, Claude, Qwen, anything) → Ships a built-in UI with human-in-the-loop support → Turn 20-click ERP/CRM workflows into one sentence → Optional Chrome extension for multi-tab agent tasks → Works on any web app SaaS, admin panels, internal tools Companies are charging $30/month for AI copilots built on this exact idea. This is 3 lines of code. Your users. Your interface. The AI copilot layer for every web app just got open sourced. 1.6K stars. 100% Open Source. (Link in the comments)

Ihtesham Ali

135,634 views • 7 months ago

🚨 NVIDIA just flipped the entire AI game… and this is NOT about gaming. DeepSeek-V4-Pro is now live on their build platform. 1.6 TRILLION parameters. Yes… the largest open-source model on the planet right now. And here’s the crazy part: They’re letting you run it FREE On Blackwell GPUs in the cloud. This is the same level of hardware companies like Google, Meta, and Microsoft fight billions to access. Now it’s just… available. No waitlist. No insane setup. Just raw power. We’re watching the shift happen in real time: → From closed AI → open domination → From GPU scarcity → free access → From Big Tech control → builders winning This isn’t an update. It’s a warning shot. Who’s already testing this? Link👇

🚨 NVIDIA just flipped the entire AI game… and this is NOT about gaming. DeepSeek-V4-Pro is now live on their build platform. 1.6 TRILLION parameters. Yes… the largest open-source model on the planet right now. And here’s the crazy part: They’re letting you run it FREE On Blackwell GPUs in the cloud. This is the same level of hardware companies like Google, Meta, and Microsoft fight billions to access. Now it’s just… available. No waitlist. No insane setup. Just raw power. We’re watching the shift happen in real time: → From closed AI → open domination → From GPU scarcity → free access → From Big Tech control → builders winning This isn’t an update. It’s a warning shot. Who’s already testing this? Link👇

divyansh tiwari

29,941 views • 6 months ago

THIS ENGINEER SKIPPED 7,862 WORDS OF AI ROADMAP AND SHIPPED ON A WEEKEND a Pi Zero 2W, an IMX500 camera and a solar panel, that's the whole stack inference runs on-chip so there's no cloud, no latency and no monthly bill Spotted Dove at 0.95, King Parrot at 0.88, runs forever on sun code is open source and the 3D files are free, you just print the case and buy the parts and it works better than most paid wildlife monitoring services out there full video: code (open source): 3D print files: solar power board: save this so you actually have everything in one place when you decide to build it

THIS ENGINEER SKIPPED 7,862 WORDS OF AI ROADMAP AND SHIPPED ON A WEEKEND a Pi Zero 2W, an IMX500 camera and a solar panel, that's the whole stack inference runs on-chip so there's no cloud, no latency and no monthly bill Spotted Dove at 0.95, King Parrot at 0.88, runs forever on sun code is open source and the 3D files are free, you just print the case and buy the parts and it works better than most paid wildlife monitoring services out there full video: code (open source): 3D print files: solar power board: save this so you actually have everything in one place when you decide to build it

leopardracer

63,096 views • 5 months ago

You don't need a GPU for fast studio grade voice cloning anymore. Qwen3 TTS (1.7B Q4_K_M) + mainline llama.cpp is officially the fastest way to generate zero shot voice clones using 100% pure CPU execution. Following up on my last post where we ran the Q8 model on a GPU, we just took local C++ voice synthesis a massive step further. The open source community quantized Alibaba's SOTA Qwen3 TTS model down to Q4_K_M GGUF, completely freeing local audio pipelines from dedicated graphics hardware. Here is the real world benchmark and hardware breakdown of running SOTA voice cloning on CPU: # Architecture & Model Setup Using Qwen3-TTS-12Hz-1.7B-Base-Q4_K_M.gguf paired with the 8 bit multimodal projector (mmproj-Q8_0.gguf), llama.cpp executes the entire pipeline in pure C++. No PyTorch, no CUDA dependencies, and no VRAM bottlenecks. # Real-World Memory Footprint - Baseline RAM: 1.6 GB system idle. - Peak Generation RAM: 8 GB RAM during active voice synthesis. - Requirement: Any basic machine with at least 8 GB of system RAM can run this easily. # Real World CPU Benchmarks - Google Colab Free Tier (Throttled 2 Core CPU): Synthesizes a 5 sec studio quality audio clip (~8 words) in 45 seconds. - Modern Consumer CPU (Intel i5/i7 13th/14th Gen or AMD Ryzen 7000/9000): generation should drop to 5 to 20 seconds (nearly 1:1 real-time generation speed!). # Zero Shot Voice Cloning Quality Pass any 5 to 20 second .wav audio sample to the C++ engine using the --tts-speaker-file flag. It yields clean, natural sounding cloned speech with virtually zero quality loss compared to unquantized FP16 weights. To make testing seamless, I built an updated zero config Google Colab notebook. It pulls the official pre built llama.cpp CPU binaries (zero compilation time!) launches a live Gradio web app right in your browser. Record a 5 second clip from your mic (or drop a .mp3, .wav file), type text, and generate cloned audio on CPU. Native C++ audio models are making edge based, offline AI voice agents a reality. Links to the free Q4 CPU Colab notebook and the Q4_K_M GGUF HuggingFace repository are in the replies below! Which models have you been running on your CPUs? What CPU hardware are you using for local inference?

You don't need a GPU for fast studio grade voice cloning anymore. Qwen3 TTS (1.7B Q4_K_M) + mainline llama.cpp is officially the fastest way to generate zero shot voice clones using 100% pure CPU execution. Following up on my last post where we ran the Q8 model on a GPU, we just took local C++ voice synthesis a massive step further. The open source community quantized Alibaba's SOTA Qwen3 TTS model down to Q4_K_M GGUF, completely freeing local audio pipelines from dedicated graphics hardware. Here is the real world benchmark and hardware breakdown of running SOTA voice cloning on CPU: # Architecture & Model Setup Using Qwen3-TTS-12Hz-1.7B-Base-Q4_K_M.gguf paired with the 8 bit multimodal projector (mmproj-Q8_0.gguf), llama.cpp executes the entire pipeline in pure C++. No PyTorch, no CUDA dependencies, and no VRAM bottlenecks. # Real-World Memory Footprint - Baseline RAM: 1.6 GB system idle. - Peak Generation RAM: 8 GB RAM during active voice synthesis. - Requirement: Any basic machine with at least 8 GB of system RAM can run this easily. # Real World CPU Benchmarks - Google Colab Free Tier (Throttled 2 Core CPU): Synthesizes a 5 sec studio quality audio clip (~8 words) in 45 seconds. - Modern Consumer CPU (Intel i5/i7 13th/14th Gen or AMD Ryzen 7000/9000): generation should drop to 5 to 20 seconds (nearly 1:1 real-time generation speed!). # Zero Shot Voice Cloning Quality Pass any 5 to 20 second .wav audio sample to the C++ engine using the --tts-speaker-file flag. It yields clean, natural sounding cloned speech with virtually zero quality loss compared to unquantized FP16 weights. To make testing seamless, I built an updated zero config Google Colab notebook. It pulls the official pre built llama.cpp CPU binaries (zero compilation time!) launches a live Gradio web app right in your browser. Record a 5 second clip from your mic (or drop a .mp3, .wav file), type text, and generate cloned audio on CPU. Native C++ audio models are making edge based, offline AI voice agents a reality. Links to the free Q4 CPU Colab notebook and the Q4_K_M GGUF HuggingFace repository are in the replies below! Which models have you been running on your CPUs? What CPU hardware are you using for local inference?

Alok

105,756 views • 2 months ago