Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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...

acemusicAI's profile picture

ACE Music

2,305 subscribers

1,057,390 Aufrufe • vor 6 Monaten •via X (Twitter)

MusikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

There's a free, open-source music generator that claims to land between Suno v4.5 and Suno v5 in quality, and it'll run locally on a GPU with under 4GB of VRAM. It's called ACE-Step 1.5. → Free to try instantly, no GPU, no install → Generates a full song in under 10 seconds on a regular RTX 3090 → Train it on your own sound: feed it about 8 of your own songs and it learns your style as a LoRA in about an hour Paste a genre and mood, get back a finished song with vocals, in any of 50+ languages.
0:30

There's a free, open-source music generator that claims to land between Suno v4.5 and Suno v5 in quality, and it'll run locally on a GPU with under 4GB of VRAM. It's called ACE-Step 1.5. → Free to try instantly, no GPU, no install → Generates a full song in under 10 seconds on a regular RTX 3090 → Train it on your own sound: feed it about 8 of your own songs and it learns your style as a LoRA in about an hour Paste a genre and mood, get back a finished song with vocals, in any of 50+ languages.

Simplifying AI

14,864 Aufrufe • vor 2 Tagen

Suno just got replaced entirely🤯 Someone built ACE-Step UI, a Spotify-style interface for ACE-Step 1.5 that generates full songs with vocals up to 4+ minutes, completely locally on your own GPU. 100% Free. Open-Source and Local
0:28

Suno just got replaced entirely🤯 Someone built ACE-Step UI, a Spotify-style interface for ACE-Step 1.5 that generates full songs with vocals up to 4+ minutes, completely locally on your own GPU. 100% Free. Open-Source and Local

Oliver Prompts

69,290 Aufrufe • vor 1 Monat

Run ACE-Step-v1.5 on your computer, with 1 click. Do we finally have a true FREE SUNO alternative? Try yourself and find out! I wrote a 1-click launcher for the official Gradio app. It's high quality, fast, open source. Might be the LTX-2 moment for song generation AI!
0:43

Run ACE-Step-v1.5 on your computer, with 1 click. Do we finally have a true FREE SUNO alternative? Try yourself and find out! I wrote a 1-click launcher for the official Gradio app. It's high quality, fast, open source. Might be the LTX-2 moment for song generation AI!

cocktail peanut

54,227 Aufrufe • vor 6 Monaten

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.
20:45

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

704,956 Aufrufe • vor 1 Monat

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!
0:58

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

LMSYS Org

11,216 Aufrufe • vor 2 Monaten

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source
0:28

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Superman

281,950 Aufrufe • vor 28 Tagen

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!
2:36

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,866 Aufrufe • vor 3 Jahren

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.
3:09

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

QVAC

108,780 Aufrufe • vor 5 Monaten

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.
0:33

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,413 Aufrufe • vor 4 Monaten

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.
0:26

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 Aufrufe • vor 23 Tagen

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇
8:20

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

Julian Goldie SEO

59,167 Aufrufe • vor 6 Monaten

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike
1:20

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

Harry Stebbings

63,738 Aufrufe • vor 2 Monaten

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:
6:05

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,621 Aufrufe • vor 2 Jahren

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

47,954 Aufrufe • vor 1 Monat

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:
0:54

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:

NVIDIA AI Developer

100,506 Aufrufe • vor 1 Jahr

Suno is limiting downloads, basically making a lot of the songs you make locked in their 'walled garden'. One of their main competitors, Udio, did the same thing after a settlement with UMG that restricts any downloads. This is 100% an injunction from the music labels who want to limit the "damage" that AI does to the profitability of music. There are two viable alternatives... >Minimax music 3.0. It is currently free to use up to 500 songs a day as long as your account qualifies for beta testing their music model, which should be anyone. It is a closed-weight model, but there are no restrictions on what you download and how much you download. The music quality is not as good as Udio or Suno, but it's pretty close overall, and it can understand very complex prompts to guide music generation. >Open-source music is not a very good alternative... but right now SongGeneration-LeVo2 is the best AI music model that's open-source right now. The music I put on the post is one such generation that I created on my PC. The problem is that it's hard to use. The comfyUI version requires installation on a separate portable install, specific transformer and flash attention versions, and additional libraries installed. The required models and checkpoints are scattered around Hugging Face, and some of the links from the original repo are dead. There are not many English guides, and most of the training data is in Chinese, so it struggles with English lyrics. To some extent, the demand for music generation isn't that high, compared to images and videos, so overall not many alternatives are around.
1:32

Suno is limiting downloads, basically making a lot of the songs you make locked in their 'walled garden'. One of their main competitors, Udio, did the same thing after a settlement with UMG that restricts any downloads. This is 100% an injunction from the music labels who want to limit the "damage" that AI does to the profitability of music. There are two viable alternatives... >Minimax music 3.0. It is currently free to use up to 500 songs a day as long as your account qualifies for beta testing their music model, which should be anyone. It is a closed-weight model, but there are no restrictions on what you download and how much you download. The music quality is not as good as Udio or Suno, but it's pretty close overall, and it can understand very complex prompts to guide music generation. >Open-source music is not a very good alternative... but right now SongGeneration-LeVo2 is the best AI music model that's open-source right now. The music I put on the post is one such generation that I created on my PC. The problem is that it's hard to use. The comfyUI version requires installation on a separate portable install, specific transformer and flash attention versions, and additional libraries installed. The required models and checkpoints are scattered around Hugging Face, and some of the links from the original repo are dead. There are not many English guides, and most of the training data is in Chinese, so it struggles with English lyrics. To some extent, the demand for music generation isn't that high, compared to images and videos, so overall not many alternatives are around.

Emerald Apple

16,152 Aufrufe • vor 14 Tagen

six months ago this wasn't happening on 8gb vram. running unsloth's Q4_K_XL quant of gemma 4 26b-a4b-it-qat, a sparse MoE model with only 4b active params on a single rtx 4060 laptop gpu, 8gb vram, 20+ tok/s decode. no cloud, no api, no offload hacks. just a gaming laptop on battery. what makes it fit: google's QAT (quantization aware training), plus MTP (multi token prediction) support in the latest llama.cpp builds. that combo is the single biggest unlock for local inference on low vram. rtx 3060, rtx 3070, gtx 1070, gtx 1080, rtx 4050, rtx 4060, rtx 5050, rtx 5060 — any 6-8gb consumer gpu, old or new — this model runs on it. world cup season, so i told it to build a soccer themed flappy bird clone. one shot, zero iteration, fully playable. six months ago an 8gb model could barely clone vanilla flappy bird. now it's shipping a themed game from a sparse MoE model running locally on a laptop battery. inference benchmarks: - decode throughput: 30 tok/s - context: 64k. this is the real unlock. 64k ctx is what makes a hermes agent loop viable locally on this model, not just single-turn chat. llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 -cmoe --port 8080 game's deployed on my own site, built and shipped end to end with open source llm, zero closed source api dependency in the pipeline. link in the description. gguf weights on huggingface, link in the comments. pull it down, run it on whatever 8gb card is sitting in your rig. try the game and tell me your score and what you want in v2. local llms on consumer gpus stopped being a meme.
0:20

six months ago this wasn't happening on 8gb vram. running unsloth's Q4_K_XL quant of gemma 4 26b-a4b-it-qat, a sparse MoE model with only 4b active params on a single rtx 4060 laptop gpu, 8gb vram, 20+ tok/s decode. no cloud, no api, no offload hacks. just a gaming laptop on battery. what makes it fit: google's QAT (quantization aware training), plus MTP (multi token prediction) support in the latest llama.cpp builds. that combo is the single biggest unlock for local inference on low vram. rtx 3060, rtx 3070, gtx 1070, gtx 1080, rtx 4050, rtx 4060, rtx 5050, rtx 5060 — any 6-8gb consumer gpu, old or new — this model runs on it. world cup season, so i told it to build a soccer themed flappy bird clone. one shot, zero iteration, fully playable. six months ago an 8gb model could barely clone vanilla flappy bird. now it's shipping a themed game from a sparse MoE model running locally on a laptop battery. inference benchmarks: - decode throughput: 30 tok/s - context: 64k. this is the real unlock. 64k ctx is what makes a hermes agent loop viable locally on this model, not just single-turn chat. llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 -cmoe --port 8080 game's deployed on my own site, built and shipped end to end with open source llm, zero closed source api dependency in the pipeline. link in the description. gguf weights on huggingface, link in the comments. pull it down, run it on whatever 8gb card is sitting in your rig. try the game and tell me your score and what you want in v2. local llms on consumer gpus stopped being a meme.

Alok

61,660 Aufrufe • vor 2 Monaten

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.
2:52

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 Aufrufe • vor 2 Jahren

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.
0:41

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

RetroChainer

16,971 Aufrufe • vor 14 Tagen