Daniel (Unsloth) PRO

danielhanchen's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 5 hours ago

unsloth/Mistral-Small-4-119B-2603-GGUF

119B • Updated about 4 hours ago • 27.6k • 60

updated a model about 7 hours ago

unsloth/Mistral-Small-4-119B-2603

119B • Updated about 7 hours ago • 161 • 4

New activity in unsloth/Qwen3.6-35B-A3B-GGUF about 9 hours ago

Qwen3.6 GGUF Benchmarks

🔥👍 14

24

#10 opened 2 days ago by

danielhanchen

New activity in unsloth/Qwen3.6-35B-A3B-GGUF 2 days ago

Qwen 3.6 is much slower than Qwen 3.5 for the same quatization: UD-Q4_K_XL

9

#8 opened 2 days ago by

adr-insc

ollama support

👀 1

2

#6 opened 3 days ago by

madhutter

New activity in unsloth/gemma-4-26B-A4B-it-GGUF 2 days ago

[BUG] Vision capability not working for Gemma4 GGUF in Ollama

2

#31 opened 5 days ago by

notuncommon

updated 3 models 3 days ago

unsloth/Qwen3.6-35B-A3B-MLX-8bit

Image-Text-to-Text • 10B • Updated 2 days ago • 4.92k • 4

unsloth/Qwen3.6-35B-A3B-UD-MLX-3bit

Image-Text-to-Text • 5B • Updated 2 days ago • 1.79k • 2

unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit

Image-Text-to-Text • 6B • Updated 2 days ago • 4.89k • 11

published 3 models 3 days ago

unsloth/Qwen3.6-35B-A3B-MLX-8bit

Image-Text-to-Text • 10B • Updated 2 days ago • 4.92k • 4

unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit

Image-Text-to-Text • 6B • Updated 2 days ago • 4.89k • 11

unsloth/Qwen3.6-35B-A3B-UD-MLX-3bit

Image-Text-to-Text • 5B • Updated 2 days ago • 1.79k • 2

New activity in unsloth/Qwen3.6-35B-A3B-GGUF 3 days ago

CUDA 13.2 causes gibberish for UD-IQ4_XS quant on llama.cpp (b8815/latest)

6

#3 opened 3 days ago by

CodeFault

2-bit Qwen3.6 Tool-calling is amazing!!

🚀 13

6

#2 opened 3 days ago by

danielhanchen

liked a model 3 days ago

Qwen/Qwen3.6-35B-A3B

Image-Text-to-Text • 36B • Updated 5 days ago • 209k • 909

posted an update 3 days ago

view post

Post

2352

Qwen3.6-35B-A3B can now be run locally! 💜

The model is the strongest mid-sized LLM on nearly all benchmarks.

Run on 23GB RAM via Unsloth Dynamic GGUFs.

GGUFs to run: unsloth/Qwen3.6-35B-A3B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.6

See translation

• 
• 

• 
• 
• 
• 13 replies

·

😎

8

8

🔥

6

6

🤗

1

1

+

Reply

New activity in unsloth/Qwen3.6-35B-A3B-GGUF 3 days ago

where is the mmproj ? or this one does not support vision

4

#1 opened 3 days ago by

pt-ml

liked a model 3 days ago

unsloth/Qwen3.6-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 3 days ago • 662k • 494

published 2 models 3 days ago

unsloth/Qwen3.6-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 3 days ago • 662k • 494

unsloth/Qwen3.6-35B-A3B

Image-Text-to-Text • 36B • Updated 3 days ago • 4.51k • 9