Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

ACE-Step 1.5. Excited for this model! Can't wait to test it - pro-grade music gen; full songs in <10s @ RTX 3090; - works on <4GB VRAM; - covers, repainting, & vocal-to-BGM across 50+ languages; - outperforms commercial models.

wildmindai's profile picture

Wildminder

4,846 subscribers

14,886 Aufrufe • vor 5 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

ACE-Step 1.5 just dropped 🔥 - Full song in <10 seconds on RTX 3090 - Only 4GB VRAM needed - 50+ languages - MIT license - COMMERCIAL USE OK (legally trained!) This is Suno-killer territory. Open source wins again. 🔗 #Suno #MusicAI #OpenSource #udio #aimusic #acestep
1:09

ACE-Step 1.5 just dropped 🔥 - Full song in <10 seconds on RTX 3090 - Only 4GB VRAM needed - 50+ languages - MIT license - COMMERCIAL USE OK (legally trained!) This is Suno-killer territory. Open source wins again. 🔗 #Suno #MusicAI #OpenSource #udio #aimusic #acestep

Vali Neagu

93,394 Aufrufe • vor 5 Monaten

This AI is ridiculous - Makes studio grade songs in seconds - Free &amp; open source - Runs on low VRAM or just CPU Full Ace-Step 1.5 tutorial: God bless ACE Music
0:55

This AI is ridiculous - Makes studio grade songs in seconds - Free &amp; open source - Runs on low VRAM or just CPU Full Ace-Step 1.5 tutorial: God bless ACE Music

⚡AI Search⚡

15,105 Aufrufe • vor 5 Monaten

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song under 2s on A100 Local: ~4GB VRAM, under 10s on RTX 3090 LoRA: train your own style with a few songs License: MIT, free for commercial use Data: fully authorized plus synthetic The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.
4:40

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song under 2s on A100 Local: ~4GB VRAM, under 10s on RTX 3090 LoRA: train your own style with a few songs License: MIT, free for commercial use Data: fully authorized plus synthetic The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.

ACE Music

1,055,212 Aufrufe • vor 5 Monaten

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:
0:22

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

Harman

47,636 Aufrufe • vor 20 Tagen

"The War is at an inflection point-US needs to step back or it enters a dangerous phase of escalation"- @AmbKCSingh Lt Gen Satish Dua 🇮🇳 @ChitraSD in this must watch on another day of chaotic signalling from Washington &amp; China's Entry into Mediatory Role. In full
12:51

"The War is at an inflection point-US needs to step back or it enters a dangerous phase of escalation"- @AmbKCSingh Lt Gen Satish Dua 🇮🇳 @ChitraSD in this must watch on another day of chaotic signalling from Washington &amp; China's Entry into Mediatory Role. In full

barkha dutt

14,200 Aufrufe • vor 4 Monaten

A $351 MINI PC IS RUNNING 26-BILLION-PARAMETER AI MODELS AT 20 TOKENS/SEC AND HERMES AGENT ON TOP OF IT This is the Minisforum UM790 Pro. AMD Ryzen 9 7940HS, Radeon 780M iGPU, 48GB DDR5. The BIOS reports the GPU has 4GB of VRAM Here's the part people get wrong. The 780M has no dedicated VRAM at all it borrows from system RAM. Vulkan ignores the BIOS number and reads the full 48GB pool directly That's the whole trick. 21+ GB allocated to model weights on a "4GB" GPU. Because the models are MoE, only 4 billion of the parameters activate per token a fraction of the reads a dense model needs. That's why 20 tok/s works here Gemma 4 26B MoE holds 19.5 tok/s with 196K context. Qwen3.5-35B-A3B holds 20.8. Nemotron Cascade 2 clears 24.8. A dense 31B, by contrast, drops to 4 tok/s it reads the entire model every token, no way around it On top: Hermes Agent, full agentic workflows terminal, file ops, web, 40+ tools against local models only. No API keys. The wall between you and a usable local agent used to be a GPU you couldn't afford. Now it's a BIOS setting most people never check Bookmark this & Try it yourself ↓
1:22

A $351 MINI PC IS RUNNING 26-BILLION-PARAMETER AI MODELS AT 20 TOKENS/SEC AND HERMES AGENT ON TOP OF IT This is the Minisforum UM790 Pro. AMD Ryzen 9 7940HS, Radeon 780M iGPU, 48GB DDR5. The BIOS reports the GPU has 4GB of VRAM Here's the part people get wrong. The 780M has no dedicated VRAM at all it borrows from system RAM. Vulkan ignores the BIOS number and reads the full 48GB pool directly That's the whole trick. 21+ GB allocated to model weights on a "4GB" GPU. Because the models are MoE, only 4 billion of the parameters activate per token a fraction of the reads a dense model needs. That's why 20 tok/s works here Gemma 4 26B MoE holds 19.5 tok/s with 196K context. Qwen3.5-35B-A3B holds 20.8. Nemotron Cascade 2 clears 24.8. A dense 31B, by contrast, drops to 4 tok/s it reads the entire model every token, no way around it On top: Hermes Agent, full agentic workflows terminal, file ops, web, 40+ tools against local models only. No API keys. The wall between you and a usable local agent used to be a GPU you couldn't afford. Now it's a BIOS setting most people never check Bookmark this & Try it yourself ↓

slash1s

35,742 Aufrufe • vor 1 Monat

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by Inworld AI: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!
5:09

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by Inworld AI: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Santiago

69,439 Aufrufe • vor 6 Monaten

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider
0:29

NVIDIA is giving away free access to 140+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: GLM 5.2, MiniMax M3, Nemotron-3-Ultra-550B-A55B, Kimi K2.7, and 130+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "z-ai/glm-5.2" model = "minimaxai/minimax-m3" model = "nvidia/nemotron-3-ultra-550b-a55b" model = "moonshot-ai/kimi-k2.7" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free with this many models in one place, it is also the easiest way to test which one actually fits your agent before you commit to a paid provider

Mr. Buzzoni

117,911 Aufrufe • vor 15 Tagen

Eval scores in 2026 are broken. MMLU at 91%+, GSM8K at 94%+, yet models still can't handle basic multi-step tasks. And reported scores don't even agree across model cards, papers, and platforms. We just shipped Community Evals on Hugging Face: - Benchmark datasets now host live leaderboards (MMLU-Pro, GPQA, HLE) - Scores live in model repos as versioned YAML - Anyone can submit evals to any model via PR without merging. - Verified badges for reproducible runs via Inspect AI This won't fix saturation or stop test set contamination. But it makes the game visible. What was evaluated, how, when, and by whom. Done trusting black-box leaderboards. Time to decentralize evals.
0:29

Eval scores in 2026 are broken. MMLU at 91%+, GSM8K at 94%+, yet models still can't handle basic multi-step tasks. And reported scores don't even agree across model cards, papers, and platforms. We just shipped Community Evals on Hugging Face: - Benchmark datasets now host live leaderboards (MMLU-Pro, GPQA, HLE) - Scores live in model repos as versioned YAML - Anyone can submit evals to any model via PR without merging. - Verified badges for reproducible runs via Inspect AI This won't fix saturation or stop test set contamination. But it makes the game visible. What was evaluated, how, when, and by whom. Done trusting black-box leaderboards. Time to decentralize evals.

Ben Burtenshaw

19,259 Aufrufe • vor 5 Monaten

Anyone with 8GB or 12GB VRAM setups needs to understand that "-ncmoe" is the key flag to boost performance on llama.cpp Here are my results for Qwen3.6 35B A3B, with 64k q8_0 context on a 8GB RTX 3070Ti: ⚪️ no flag → 8.7 tok/s RAM: 13.6GB & VRAM: 7.8GB 🔴 -ncmoe 35 → 27.5 tok/s RAM: 12.1GB & VRAM: 4.3GB 🟢 -ncmoe 30 → 32.5 tok/s RAM: 12GB & VRAM: 5.6GB 🔵 -ncmoe 25 → 40.9 tok/s RAM: 12GB & VRAM: 6.9GB Please note the ram and vram usage you see are total usage of a windows pc, with the model running. My friend's setup: 8GB VRAM and 16GB RAM. You can boost performance by switching to Linux, just something to keep in mind. Basically, this flag keeps the MoE experts in the first X layers on your CPU + RAM, instead of eating all your VRAM straight away. This is a smart hybrid offload way that lets you run bigger models without OOM while keeping the rest on your GPU for speed. As we can see on the data, there's a sweet spot. When we lower it from 35 to 25, speed bumps +50% because there are more layers on your GPU (look at the VRAM usage). The key here is to play around with the number and fit as much as possible on your VRAM, goal is to have 1GB/800MB headroom to avoid stress. ↓ server flags below
0:37

Anyone with 8GB or 12GB VRAM setups needs to understand that "-ncmoe" is the key flag to boost performance on llama.cpp Here are my results for Qwen3.6 35B A3B, with 64k q8_0 context on a 8GB RTX 3070Ti: ⚪️ no flag → 8.7 tok/s RAM: 13.6GB & VRAM: 7.8GB 🔴 -ncmoe 35 → 27.5 tok/s RAM: 12.1GB & VRAM: 4.3GB 🟢 -ncmoe 30 → 32.5 tok/s RAM: 12GB & VRAM: 5.6GB 🔵 -ncmoe 25 → 40.9 tok/s RAM: 12GB & VRAM: 6.9GB Please note the ram and vram usage you see are total usage of a windows pc, with the model running. My friend's setup: 8GB VRAM and 16GB RAM. You can boost performance by switching to Linux, just something to keep in mind. Basically, this flag keeps the MoE experts in the first X layers on your CPU + RAM, instead of eating all your VRAM straight away. This is a smart hybrid offload way that lets you run bigger models without OOM while keeping the rest on your GPU for speed. As we can see on the data, there's a sweet spot. When we lower it from 35 to 25, speed bumps +50% because there are more layers on your GPU (look at the VRAM usage). The key here is to play around with the number and fit as much as possible on your VRAM, goal is to have 1GB/800MB headroom to avoid stress. ↓ server flags below

left curve dev

166,063 Aufrufe • vor 2 Monaten

V3 IS HERE 💥 We are excited to introduce our first model capable of producing radio-quality music. v3 allows you to make full, 2 minute songs in seconds and is now available to all users. Try it for free here: Thank you to our Pro + Premier members; v3 incorporates your feedback and features several improvements, most notably: 🎧 Better audio quality 🎵 More styles and genres 🎯 Improved prompt adherence, including fewer hallucinations and more graceful endings Read more on our blog:
0:47

V3 IS HERE 💥 We are excited to introduce our first model capable of producing radio-quality music. v3 allows you to make full, 2 minute songs in seconds and is now available to all users. Try it for free here: Thank you to our Pro + Premier members; v3 incorporates your feedback and features several improvements, most notably: 🎧 Better audio quality 🎵 More styles and genres 🎯 Improved prompt adherence, including fewer hallucinations and more graceful endings Read more on our blog:

Suno

476,543 Aufrufe • vor 2 Jahren

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.
0:30

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

AI at Meta

2,265,118 Aufrufe • vor 1 Jahr

Alibaba made Qwen 3.8 Max free on Qoder Desktop for 14 days it's their 2.4T parameter model. rivals Fable 5 on coding benchmarks. runs in a desktop IDE. what you get for $0: -2.4 trillion parameters -Qwen3.8-Max-Preview in a full agentic IDE -code completion, test generation, file editing -2-week Pro trial, then 90-98% off preview pricing what this replaces: -Fable 5 at $30/M output tokens -$20/mo Pro coding subs how to set it up (2 min): 1. Download at 2. Sign up with email 3. Add Qwen3.8-Max-Preview in Settings → Models Works on macOS, Windows, Linux. Important: 2-week free trial. No card needed. Preview pricing after is 90-98% off. Use it before they take it off
0:20

Alibaba made Qwen 3.8 Max free on Qoder Desktop for 14 days it's their 2.4T parameter model. rivals Fable 5 on coding benchmarks. runs in a desktop IDE. what you get for $0: -2.4 trillion parameters -Qwen3.8-Max-Preview in a full agentic IDE -code completion, test generation, file editing -2-week Pro trial, then 90-98% off preview pricing what this replaces: -Fable 5 at $30/M output tokens -$20/mo Pro coding subs how to set it up (2 min): 1. Download at 2. Sign up with email 3. Add Qwen3.8-Max-Preview in Settings → Models Works on macOS, Windows, Linux. Important: 2-week free trial. No card needed. Preview pricing after is 90-98% off. Use it before they take it off

painn

99,370 Aufrufe • vor 7 Tagen

look anon, those of you who kept saying local AI is not there yet, who said open source can't compete, who said you need cloud APIs to get anything serious done, look at this gameplay for one minute. every pixel on this screen was written by one model, in one shot, on a single rtx 3090 with 24gb of vram. the model is qwen 3.6 27b dense q4. the harness is hermes agent. the hardware is a single consumer card you can buy used for 900 dollars. the prompt is open source on github. every claim verifiable, on your own desk. if your local AI take is from 2024, update it. the consumer tier is shipping work that was supposed to need 8 gpus and an api key. open source moved the floor while the rest of the field was busy explaining why it cannot. 24gb tier owners are eating ramen with half boiled egg and double chocolate.
1:39

look anon, those of you who kept saying local AI is not there yet, who said open source can't compete, who said you need cloud APIs to get anything serious done, look at this gameplay for one minute. every pixel on this screen was written by one model, in one shot, on a single rtx 3090 with 24gb of vram. the model is qwen 3.6 27b dense q4. the harness is hermes agent. the hardware is a single consumer card you can buy used for 900 dollars. the prompt is open source on github. every claim verifiable, on your own desk. if your local AI take is from 2024, update it. the consumer tier is shipping work that was supposed to need 8 gpus and an api key. open source moved the floor while the rest of the field was busy explaining why it cannot. 24gb tier owners are eating ramen with half boiled egg and double chocolate.

Sudo su

29,584 Aufrufe • vor 2 Monaten

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench is the largest and most comprehensive benchmark ever released for evaluating text-to-video generation. It includes a collection of 1,000+ prompts that cover concepts ranging from detailed human activity to animals, physics, unusual subjects and more — with broad coverage across different motion levels. Movie Gen Audio Bench is a first-of-its-kind benchmark aimed at evaluating video-to-audio and (text+video)-to-audio generation. It includes 527 generated videos and associated sound effects and music prompts covering a diverse set of ambient environments and sound effects. To enable fair and easy comparison to our models for future works, these new benchmarks include non cherry-picked generated videos and audio from Movie Gen. In releasing these new benchmarks we hope to promote fair & extensive evaluations in media generation research to enable greater progress in this field.
0:23

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench is the largest and most comprehensive benchmark ever released for evaluating text-to-video generation. It includes a collection of 1,000+ prompts that cover concepts ranging from detailed human activity to animals, physics, unusual subjects and more — with broad coverage across different motion levels. Movie Gen Audio Bench is a first-of-its-kind benchmark aimed at evaluating video-to-audio and (text+video)-to-audio generation. It includes 527 generated videos and associated sound effects and music prompts covering a diverse set of ambient environments and sound effects. To enable fair and easy comparison to our models for future works, these new benchmarks include non cherry-picked generated videos and audio from Movie Gen. In releasing these new benchmarks we hope to promote fair & extensive evaluations in media generation research to enable greater progress in this field.

AI at Meta

156,273 Aufrufe • vor 1 Jahr

【1st Free Model Giveaway】 This is a model I did for both art and rig! And I'm now giving it away for free! Things included in this model: - My personal tier 4 level rig - 8 Expressions - Capturable tongue out - Full set of VBridger parameters I can provide (8 in total) How to get it: - Follow, like AND retweet THIS tweet to get both model and copyright! - Would be better if there were comments! - And if you can please follow me on Kofi too!!! - I can't monitor each person for this so PLEASE be self-possessed! - The model is now avaliable at for free! Notice: - VBridger parameters need VBridger plugin on Steam, all config are set; Be aware: only cheekpuff, mouthX and TongueOut are positive parameters, others are all optimize params for mouth&face capture! - Expresssion's config are all set too, hotkey 1-8, which are shy, black face, scared face, circle eyes, arrow eyes, sparkle eyes, heart eyes and angry Here're some terms about the model: - Please use requires attribution when using the model, link to my twitter page - Only people who follow, like and rt could get full access to the model! I can't monitor each person for this so PLEASE be self-possessed!!! - Commercial copyright is allowed for commercial stream, but CANT be used for printing, reselling and other activities like this! - The final interpretation belongs to me (Kanijam) - I just want to mention again please be self-possessed on both getting and using it!!! I might upgrade the model & sharing more free models in the future so PLEASE keep a good community environment!!!
3:34

【1st Free Model Giveaway】 This is a model I did for both art and rig! And I'm now giving it away for free! Things included in this model: - My personal tier 4 level rig - 8 Expressions - Capturable tongue out - Full set of VBridger parameters I can provide (8 in total) How to get it: - Follow, like AND retweet THIS tweet to get both model and copyright! - Would be better if there were comments! - And if you can please follow me on Kofi too!!! - I can't monitor each person for this so PLEASE be self-possessed! - The model is now avaliable at for free! Notice: - VBridger parameters need VBridger plugin on Steam, all config are set; Be aware: only cheekpuff, mouthX and TongueOut are positive parameters, others are all optimize params for mouth&face capture! - Expresssion's config are all set too, hotkey 1-8, which are shy, black face, scared face, circle eyes, arrow eyes, sparkle eyes, heart eyes and angry Here're some terms about the model: - Please use requires attribution when using the model, link to my twitter page - Only people who follow, like and rt could get full access to the model! I can't monitor each person for this so PLEASE be self-possessed!!! - Commercial copyright is allowed for commercial stream, but CANT be used for printing, reselling and other activities like this! - The final interpretation belongs to me (Kanijam) - I just want to mention again please be self-possessed on both getting and using it!!! I might upgrade the model & sharing more free models in the future so PLEASE keep a good community environment!!!

Kanijam | L2D COMMISSION CLOSE

48,354 Aufrufe • vor 3 Jahren

I nearly 2x'd the speed while only using +1GB VRAM with the new MTP update in llama.cpp 🤯 You need to add these flags to start using it: --spec-type draft-mtp \ --spec-draft-p-min 0.75 \ --spec-draft-n-max 2 My results with Qwen3.6 27B on a single RTX 5080 ↓ ⚪️ no flag (without mtp) → 54.3 tok/s with 13.26GB VRAM 🔵 --spec-draft-n-max 2 → 90.7 tok/s with 14.29GB VRAM 🔴 --spec-draft-n-max 2 --spec-draft-p-min 0.75 → 93.9 tok/s with 14.30GB VRAM 🟢 --spec-draft-n-max 6 --spec-draft-p-min 0.75 → 93.9 tok/s with 14.87GB VRAM Increasing to 6 draft tokens didn't help my setup for some reason. I made sure to test with a low context length to have enough headroom and eliminate risk of vram stress. From my understanding: 1) The speed gains are very task-dependent. You need to test across a wide range of tasks to get a realistic idea of the benefits 2) We’re already running heavily quantized GGUF models (Q3, Q4, Q6, etc.), so we already benefit from strong speed/performance thanks to the reduced size. That’s why some people are seeing little to no improvement compared to MLX or other quantized versions The progress over the past few days has been insane to say the least. However, MTP now consumes significantly more VRAM. Personally 16GB just isn't enough to use MTP and run it with a good context size. Time to upgrade lads, 24GB+ users are eating GOOD today 🔥 Full setup below ↓
0:33

I nearly 2x'd the speed while only using +1GB VRAM with the new MTP update in llama.cpp 🤯 You need to add these flags to start using it: --spec-type draft-mtp \ --spec-draft-p-min 0.75 \ --spec-draft-n-max 2 My results with Qwen3.6 27B on a single RTX 5080 ↓ ⚪️ no flag (without mtp) → 54.3 tok/s with 13.26GB VRAM 🔵 --spec-draft-n-max 2 → 90.7 tok/s with 14.29GB VRAM 🔴 --spec-draft-n-max 2 --spec-draft-p-min 0.75 → 93.9 tok/s with 14.30GB VRAM 🟢 --spec-draft-n-max 6 --spec-draft-p-min 0.75 → 93.9 tok/s with 14.87GB VRAM Increasing to 6 draft tokens didn't help my setup for some reason. I made sure to test with a low context length to have enough headroom and eliminate risk of vram stress. From my understanding: 1) The speed gains are very task-dependent. You need to test across a wide range of tasks to get a realistic idea of the benefits 2) We’re already running heavily quantized GGUF models (Q3, Q4, Q6, etc.), so we already benefit from strong speed/performance thanks to the reduced size. That’s why some people are seeing little to no improvement compared to MLX or other quantized versions The progress over the past few days has been insane to say the least. However, MTP now consumes significantly more VRAM. Personally 16GB just isn't enough to use MTP and run it with a good context size. Time to upgrade lads, 24GB+ users are eating GOOD today 🔥 Full setup below ↓

left curve dev

29,946 Aufrufe • vor 2 Monaten

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.
0:20

hey if you're thinking about running qwopus (the claude opus distilled qwen 3.5 27B) as a coding agent, this might save you a few hours. i tested both the base and the distilled version on the same hardware. single RTX 3090. same prompt. same context. same everything. the only variable was the model weights. base qwen 3.5 27B built octopus invaders in 13 minutes. 1,827 lines across 11 files. zero steering. one scope bug that took 2 lines to fix. game ran. qwopus couldn't finish the same task. enemies overlapping on screen. bullets not firing. controls worked but the game was broken. i had to steer it multiple times and it still didn't produce a playable result. both run at 35 tok/s. both use thinking mode. the distilled version actually has better jinja compatibility and doesn't stall midtask like base does on claude code. for conversation and reasoning it feels sharper. but for multifile autonomous coding where the model needs to coordinate 10+ files without losing track, base wins and it's not close. distillation compresses reasoning patterns but seems to lose precision on complex coordination. the model "thinks" well but can't hold the full picture across files the way base can. tested on opencode (base) and claude code (both). next up is hermes agent framework on base. same hardware. same prompt. comparing agents now, not just models. video below. first half is the distilled model's broken game. second half is what base built on the same 3090. judge for yourself.

Sudo su

45,052 Aufrufe • vor 4 Monaten

BOOOM! WE DID IT! BRAINWAVE TO REAL-TIME MUSIC AI! It has been a life long decades quest to read brain activity and to convert it to words, and/or music, colors and/or images. Today I am very excited to announce with the assistance from Mr. Grok director of The Zero-Human Lab, we have solved brainwave to music and this is the absolute worse it will be. We found the code using an array of NeuroSky toy chips and our software pipeline connecting to open source ACE-Step 1.5 and a highly modified LoRA model we built for this. The lyric version is in testing now. This would mean that the model will interpret words from the brainwaves and music! Today we have the music side done and the quality and genera will expand. The is the worse it will sound. Your Brainwave Music™️will be cut into 2-5 minute pieces based on a number of factors. The specimen below is from a dream/hypnogogic state I was in last night and I have a recording of my thoughts after the state. The music was made in real-time and GUIDED the dream state with known technology like binaural beats (not easy to hear in this clip) and word back masking. This specimen below shows the interplay of my brain state to the music made by my brain and adjusted to produce profound insights. I solved a very difficult issue in this session with a new AI model. IT FREAKING WORKS! THIS IS OUR FUTURE OF MORE POWERFUL BRAIN FUNCTION! Our goal is to produce a portable device you wear and will be able to give real-time audio and PEMF (skull region), ultrasound (temple region) to maximize creativity and remote viewing. It is very early days but I wanted you to know first! YOUR support of my X account, just by reading this and sharing it, subscribing to my X, buying me a and becoming a member at supports this research. I will open source this at some point and build a device ANYONE can own. Thank you! I love you.
4:17

BOOOM! WE DID IT! BRAINWAVE TO REAL-TIME MUSIC AI! It has been a life long decades quest to read brain activity and to convert it to words, and/or music, colors and/or images. Today I am very excited to announce with the assistance from Mr. Grok director of The Zero-Human Lab, we have solved brainwave to music and this is the absolute worse it will be. We found the code using an array of NeuroSky toy chips and our software pipeline connecting to open source ACE-Step 1.5 and a highly modified LoRA model we built for this. The lyric version is in testing now. This would mean that the model will interpret words from the brainwaves and music! Today we have the music side done and the quality and genera will expand. The is the worse it will sound. Your Brainwave Music™️will be cut into 2-5 minute pieces based on a number of factors. The specimen below is from a dream/hypnogogic state I was in last night and I have a recording of my thoughts after the state. The music was made in real-time and GUIDED the dream state with known technology like binaural beats (not easy to hear in this clip) and word back masking. This specimen below shows the interplay of my brain state to the music made by my brain and adjusted to produce profound insights. I solved a very difficult issue in this session with a new AI model. IT FREAKING WORKS! THIS IS OUR FUTURE OF MORE POWERFUL BRAIN FUNCTION! Our goal is to produce a portable device you wear and will be able to give real-time audio and PEMF (skull region), ultrasound (temple region) to maximize creativity and remote viewing. It is very early days but I wanted you to know first! YOUR support of my X account, just by reading this and sharing it, subscribing to my X, buying me a and becoming a member at supports this research. I will open source this at some point and build a device ANYONE can own. Thank you! I love you.

Brian Roemmele

198,257 Aufrufe • vor 1 Monat

INTEL JUST SHIPPED A WORKSTATION CARD WITH TWO GPUs ON ONE PCB AND 48GB OF VRAM. FOUR CARDS GIVE A SINGLE MOTHERBOARD 192GB OF POOLED INFERENCE MEMORY FOR THE PRICE OF TWO RTX 5090s 00:14 he holds one card up to the camera, two GPU dies side by side under the cooler, each one running its own x8 PCIe lane back to the chipset the cluster sees eight discrete accelerators in software. intel's Battle Matrix stack shards a model across all eight, so a 235B parameter network loads in slices and answers requests in parallel what 192GB of VRAM unlocks: an entire 200B class model in memory without quantization. a vision agent reading 100 invoices at once. a research box that holds three frontier models loaded simultaneously, switching between them in under a second intel is the slow side of inference. nvidia is faster per token, that is the honest tradeoff. but the only other path to this much VRAM is a $40,000 nvidia rack or three networked Mac Studios four B60 cards plus the chassis lands under $5,000. power draw averages 800 watts, $55 a month in electricity. one engineer paying $400 a month for combined ChatGPT Pro and Claude Code Max pays the hardware off in less than a year
1:16

INTEL JUST SHIPPED A WORKSTATION CARD WITH TWO GPUs ON ONE PCB AND 48GB OF VRAM. FOUR CARDS GIVE A SINGLE MOTHERBOARD 192GB OF POOLED INFERENCE MEMORY FOR THE PRICE OF TWO RTX 5090s 00:14 he holds one card up to the camera, two GPU dies side by side under the cooler, each one running its own x8 PCIe lane back to the chipset the cluster sees eight discrete accelerators in software. intel's Battle Matrix stack shards a model across all eight, so a 235B parameter network loads in slices and answers requests in parallel what 192GB of VRAM unlocks: an entire 200B class model in memory without quantization. a vision agent reading 100 invoices at once. a research box that holds three frontier models loaded simultaneously, switching between them in under a second intel is the slow side of inference. nvidia is faster per token, that is the honest tradeoff. but the only other path to this much VRAM is a $40,000 nvidia rack or three networked Mac Studios four B60 cards plus the chassis lands under $5,000. power draw averages 800 watts, $55 a month in electricity. one engineer paying $400 a month for combined ChatGPT Pro and Claude Code Max pays the hardware off in less than a year

NO1ennn

48,054 Aufrufe • vor 1 Monat