317 26 276

Daniel (Unsloth) PRO

danielhanchen

https://unsloth.ai/

AI & ML interests

None yet

Recent Activity

updated a model about 2 hours ago

unsloth/Qwen3-Coder-Next

reacted to their post with ❤️ about 12 hours ago

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: https://huggingface.co/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

new activity about 13 hours ago

unsloth/Qwen3.5-397B-A17B-GGUF:How to choose MXFP4 vs Q4_K_XL on CPU + CUDA

View all activity

Organizations

updated a model about 2 hours ago

unsloth/Qwen3-Coder-Next

Text Generation • 80B • Updated about 2 hours ago • 28.3k • 13

reacted to their post with ❤️ about 12 hours ago

Post

3412

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

5 replies

New activity in unsloth/Qwen3.5-397B-A17B-GGUF about 13 hours ago

How to choose MXFP4 vs Q4_K_XL on CPU + CUDA

#1 opened 1 day ago by

SlavikF

Core dumped for me,

#3 opened about 20 hours ago by

aaron-newsome

Q3_K_XL works surprisingly fast for 3x3090 + 128 ram

🔥 6

#4 opened about 20 hours ago by

fizzacles

updated a model about 15 hours ago

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

Image-Text-to-Text • 396B • Updated about 15 hours ago • 25.8k • 110

posted an update 1 day ago

Post

3412

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

5 replies

New activity in Qwen/Qwen3.5-397B-A17B 1 day ago

Guide to Run Qwen3.5 locally! 💜

🔥 6

#14 opened 1 day ago by

danielhanchen

liked a model 1 day ago

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

Image-Text-to-Text • 396B • Updated about 15 hours ago • 25.8k • 110

updated a collection 1 day ago

Qwen3.5

Collection

Qwen3.5 is Qwen's new model family including Qwen3.5-397B-A17B. • 2 items • Updated 1 day ago • 8

published a model 1 day ago

unsloth/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 1 day ago • 72 • 4

liked a model 1 day ago

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 1 day ago • 19.6k • • 559

published a model 1 day ago

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

Image-Text-to-Text • 396B • Updated about 15 hours ago • 25.8k • 110

New activity in unsloth/Qwen3-Coder-Next-FP8-Dynamic 1 day ago

Inconsistent output

#2 opened 12 days ago by

nephepritou

updated a collection 1 day ago

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 73 items • Updated 1 day ago • 359

New activity in unsloth/MiniMax-M2.5-GGUF 1 day ago

can you share ppl graph for your quants ?

👍 3

#4 opened 2 days ago by

ox-ox

updated a model 1 day ago

unsloth/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 1 day ago • 72 • 4

updated a collection 1 day ago

Qwen3.5

Collection

Qwen3.5 is Qwen's new model family including Qwen3.5-397B-A17B. • 2 items • Updated 1 day ago • 8

posted an update 2 days ago

Post

7876

You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF