Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Qwen
/
Qwen3-30B-A3B-Thinking-2507

Text Generation
Transformers
Safetensors
qwen3_moe
conversational
Model card Files Files and versions
xet
Community
10
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

This model only scored 49 points on LiveCodeBench v6.

#10 opened 6 days ago by
wangpin

When training Qwen3-30B-A3B-Instruct-2507 using DeepSpeed Zero 3, the training progress bar gets stuck after loading the model and data.

👀 2
3
#9 opened about 1 month ago by
lynn0999

Qwen3 2507 Hybrid ??

1
#8 opened about 2 months ago by
phoebdroid

Once it admits it is wrong, it breaks

1
#7 opened 2 months ago by
Koitenshin

思考内容出现中英文混杂

1
#6 opened 2 months ago by
leoterry

How does this compare to other "1M context"-s UloRL and Unsloth?

#5 opened 2 months ago by
ljupco

Very cool, you should name this one Qwen3.1 or something.

#3 opened 3 months ago by
imoc

Using vllm 0.10.0, `reasoning content` appears in content field instead of reasoning_content with Qwen3-30B-A3B-Thinking model

3
#2 opened 3 months ago by
aweffr

Update chat template

#1 opened 3 months ago by
olegshulyakov
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs