Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
Paper • 2610.12939 • Published • 17
AI & ML interests
None defined yet.
Recent Activity
Team members 78 private
RaghavvGoel
submitted a
paper to Daily Papers 8 days ago
danielhanchen
posted an update 11 days ago
Post
4,958
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
- 5 replies
danielhanchen
posted an update 13 days ago
Post
4,033
Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2
The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).
Run & train the model via Unsloth.
GGUF: unsloth/embeddinggemma-2-GGUF
Guide: https://unsloth.ai/docs/models/embeddinggemma-2
danielhanchen
posted an update 24 days ago
danielhanchen
posted an update 27 days ago
Post
3,716
Qwen-Image-2.1 can now run locally on 12GB VRAM with Unsloth GGUFs! 🖼️
The 7B model performs on par with Nano Banana 2.0.
For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading.
GGUF: unsloth/Qwen-Image-2.1-GGUF
Guide: https://unsloth.ai/docs/models/qwen-image-2.1
The 7B model performs on par with Nano Banana 2.0.
For higher quality, you can also run Dynamic FP8 on just 6GB of VRAM via offloading.
GGUF: unsloth/Qwen-Image-2.1-GGUF
Guide: https://unsloth.ai/docs/models/qwen-image-2.1
danielhanchen
posted an update about 1 month ago
Post
6,897
Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time! 🤗🦥
The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.
GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8
The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.
GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8
- 5 replies
danielhanchen
posted an update 2 months ago
Post
7,572
Introducing Unsloth Desktop 🦥
The first desktop app to run and train models locally.
• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere
Unsloth Desktop is now available on http://unsloth.ai
and GitHub.
GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/desktop
The first desktop app to run and train models locally.
• Open-source. Runs on Mac, Windows and Linux
• Supports MLX, diffusion image/video, audio, GGUF
• Connect Claude Code and Codex to local LLMs
• 50% more accurate, self-healing tool calls + sandboxed code exec
• Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
• Train models 2× faster with 70% less VRAM
• Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
• Use Unsloth’s OpenAI-compatible API and cloud models
• Securely deploy LLMs remotely and access anywhere
Unsloth Desktop is now available on http://unsloth.ai
and GitHub.
GitHub: https://github.com/unslothai/unsloth
Blog and Guide: https://unsloth.ai/docs/desktop
- 6 replies
danielhanchen
posted an update 2 months ago
Post
3,835
DeepSeek-V4-Flash can now run 2× faster locally with DSpark! ⚡️
DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2× faster with no accuracy change.
DeepSeek-V4-Flash-0731 can reach at 120 tokens/s.
GGUFs: unsloth/DeepSeek-V4-Flash-0731-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4
DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2× faster with no accuracy change.
DeepSeek-V4-Flash-0731 can reach at 120 tokens/s.
GGUFs: unsloth/DeepSeek-V4-Flash-0731-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4
- 1 reply
danielhanchen
posted an update 3 months ago
Post
3,576
We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. 🤯
We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...
1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.
GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth
We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts...
1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s.
GGUF: unsloth/Kimi-K3-GGUF
GitHub repo: https://github.com/unslothai/unsloth
- 1 reply
danielhanchen
posted an update 3 months ago
Post
5,771
Kimi K3 can now be run locally! ✨
The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).
Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.
GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3
The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).
Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.
GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3
- 5 replies
danielhanchen
posted an update 3 months ago
Post
6,068
Introducing Unsloth for AMD 🚀
You can now train & run LLMs on your AMD hardware
• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM
GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
You can now train & run LLMs on your AMD hardware
• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM
GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
- 3 replies
danielhanchen
posted an update 3 months ago
Post
6,950
Gemma 4 is now faster and much more accurate! 🚀
Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!
Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4
Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!
Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4
- 8 replies
danielhanchen
posted an update 3 months ago
Post
5,498
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU.
Gemma-4-12B NVFP4 works on 11GB VRAM.
26B-A4B hits 13K tok/s (B200).
Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.
Blog: https://unsloth.ai/docs/basics/nvfp4
Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4
Gemma-4-12B NVFP4 works on 11GB VRAM.
26B-A4B hits 13K tok/s (B200).
Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.
Blog: https://unsloth.ai/docs/basics/nvfp4
Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4
- 3 replies
danielhanchen
posted an update 3 months ago
Post
4,945
We’re releasing new Qwen3.6 quants that run 2.5× faster on your GPU. ⚡
Qwen3.6-27B NVFP4 runs on 24GB VRAM.
35B-A3B can hit 17,561 tok/s (B200).
We also improved accuracy, tool calling, agent use, and looping.
Qwen3.6 NVFP4: https://huggingface.co/collections/unsloth/nvfp4
Guide: https://unsloth.ai/docs/models/qwen3.6#nvfp4
Qwen3.6-27B NVFP4 runs on 24GB VRAM.
35B-A3B can hit 17,561 tok/s (B200).
We also improved accuracy, tool calling, agent use, and looping.
Qwen3.6 NVFP4: https://huggingface.co/collections/unsloth/nvfp4
Guide: https://unsloth.ai/docs/models/qwen3.6#nvfp4
- 1 reply
danielhanchen
posted an update 3 months ago
Post
6,923
DeepSeek-V4 can now run locally with Unsloth GGUFs! 🐳
Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.
Run via Unsloth Studio or llama.cpp.
GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4
Run lossless DeepSeek-V4-Flash on 168GB RAM or
3-bit works on 110GB Mac, RAM, VRAM setups.
Run via Unsloth Studio or llama.cpp.
GGUF: unsloth/DeepSeek-V4-Flash-GGUF
Guide: https://unsloth.ai/docs/models/deepseek-v4
danielhanchen
posted an update 4 months ago
Post
3,779
1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5
We gave 3 models the same prompt and compared one-shot outputs.
The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s.
Which output do you like best?
GGUF: unsloth/GLM-5.2-GGUF
We gave 3 models the same prompt and compared one-shot outputs.
The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s.
Which output do you like best?
GGUF: unsloth/GLM-5.2-GGUF
- 3 replies
danielhanchen
posted an update 4 months ago
Post
4,943
Google's new DiffusionGemma can now run at 2000+ tokens/sec! ⚡
We made local DiffusionGemma inference 1.8× faster.
Run it on 18GB RAM via Unsloth Studio.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/models/diffusiongemma
We made local DiffusionGemma inference 1.8× faster.
Run it on 18GB RAM via Unsloth Studio.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/models/diffusiongemma
- 4 replies
danielhanchen
posted an update 4 months ago
Post
1,449
Google releases DiffusionGemma.✨
The new 26B-A4B diffusion text model runs locally on 18GB RAM.
Run with 4x faster text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio.
GGUF: unsloth/diffusiongemma-26B-A4B-it-GGUF
Guide: https://unsloth.ai/docs/models/diffusiongemma
The new 26B-A4B diffusion text model runs locally on 18GB RAM.
Run with 4x faster text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio.
GGUF: unsloth/diffusiongemma-26B-A4B-it-GGUF
Guide: https://unsloth.ai/docs/models/diffusiongemma
- 1 reply
danielhanchen
posted an update 4 months ago
Post
4,501
Google releases Gemma 4 QAT. ✨
You can now run Gemma 4 at 3x less memory with near original performance.
QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat
You can now run Gemma 4 at 3x less memory with near original performance.
QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat
- 1 reply
danielhanchen
posted an update 5 months ago
Post
9,548
Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.
Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.
GGUF: unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4
Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.
GGUF: unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4
- 5 replies