AI & ML interests

None defined yet.

Team members 76
private

danielhanchenΒ 
posted an update about 4 hours ago
danielhanchenΒ 
posted an update 14 days ago
danielhanchenΒ 
posted an update about 1 month ago
view post
Post
5868
Introducing Unsloth Desktop πŸ¦₯
The first desktop app to run and train models locally.

β€’ Open-source. Runs on Mac, Windows and Linux
β€’ Supports MLX, diffusion image/video, audio, GGUF
β€’ Connect Claude Code and Codex to local LLMs
β€’ 50% more accurate, self-healing tool calls + sandboxed code exec
β€’ Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac
β€’ Train models 2Γ— faster with 70% less VRAM
β€’ Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF)
β€’ Use Unsloth’s OpenAI-compatible API and cloud models
β€’ 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
Β·
danielhanchenΒ 
posted an update about 2 months ago
danielhanchenΒ 
posted an update about 2 months ago
view post
Post
2372
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
  • 1 reply
Β·
danielhanchenΒ 
posted an update about 2 months ago
view post
Post
4727
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
  • 5 replies
Β·
danielhanchenΒ 
posted an update 2 months ago
view post
Post
5312
Introducing Unsloth for AMD πŸš€
You can now train & run LLMs on your AMD hardware

β€’ We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
β€’ Works on Windows, WSL, Linux
β€’ Train Qwen, Gemma on just 3GB VRAM

GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
  • 3 replies
Β·
danielhanchenΒ 
posted an update 2 months ago
danielhanchenΒ 
posted an update 2 months ago
danielhanchenΒ 
posted an update 2 months ago
danielhanchenΒ 
posted an update 3 months ago
danielhanchenΒ 
posted an update 3 months ago
view post
Post
3447
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
  • 3 replies
Β·
danielhanchenΒ 
posted an update 3 months ago
danielhanchenΒ 
posted an update 3 months ago
danielhanchenΒ 
posted an update 4 months ago
danielhanchenΒ 
posted an update 4 months ago
view post
Post
9419
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
  • 5 replies
Β·
danielhanchenΒ 
posted an update 4 months ago
danielhanchenΒ 
posted an update 4 months ago
view post
Post
6026
We’re excited to announce that Unsloth has joined the PyTorch Ecosystem! πŸ”₯πŸ¦₯

Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! πŸ’•

Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
  • 2 replies
Β·
qgallouedecΒ 
posted an update 5 months ago
view post
Post
10901
Shipped hf-sandbox! πŸ₯‘

πŸ§ͺ Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.

Just pip install hf-sandbox.

Early days (v0.1); feedback and issues very welcome:
πŸ‘‰ https://github.com/huggingface/hf-sandbox
  • 1 reply
Β·
danielhanchenΒ 
posted an update 5 months ago
view post
Post
7816
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! πŸš€

Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing

Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth