danielhanchen (Daniel (Unsloth))

posted an update about 4 hours ago

Post

51

We collabed with HF on showing how you can use HF Jobs and Unsloth! https://huggingface.co/blog/unsloth-jobs

published an article about 5 hours ago

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

+4

about 5 hours ago

•

33

upvoted an article about 11 hours ago

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

+4

about 5 hours ago

•

33

New activity in unsloth/Qwen3.5-397B-A17B-GGUF about 15 hours ago

Is it possible to turn off thinking mode on Llama.cpp?

4

#8 opened about 22 hours ago by

alexaione

liked a model about 16 hours ago

microsoft/OptiMind-SFT

Text Generation • 21B • Updated Jan 15 • 2.35k • 94

updated a model 2 days ago

unsloth/Qwen3-Coder-Next-GGUF

Text Generation • 80B • Updated 2 days ago • 417k • 364

updated a model 3 days ago

unsloth/Qwen3-Coder-Next

Text Generation • 80B • Updated 2 days ago • 28.5k • 17

reacted to their post with ❤️ 3 days ago

Post

5448

You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.

GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.

Guide: https://unsloth.ai/docs/models/qwen3.5

9 replies

·

New activity in unsloth/Qwen3.5-397B-A17B-GGUF 3 days ago

How to choose MXFP4 vs Q4_K_XL on CPU + CUDA

2

#1 opened 4 days ago by

SlavikF

Core dumped for me,

3

#3 opened 3 days ago by

aaron-newsome

Q3_K_XL works surprisingly fast for 3x3090 + 128 ram

🔥 8

4

#4 opened 3 days ago by

fizzacles

updated a model 3 days ago

unsloth/Qwen3.5-397B-A17B-GGUF

Image-Text-to-Text • 396B • Updated 3 days ago • 58.5k • 154

posted an update 4 days ago

Post

5448

You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.

GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.

Guide: https://unsloth.ai/docs/models/qwen3.5