Qwen
/

Qwen3-Omni-30B-A3B-Thinking

Model card Files Files and versions

Resources

View closed (0)

Severe generation length bottleneck (hardcoded at 1024 tokens) in Qwen3OmniMoeForConditionalGeneration during greedy search / custom generation loop

#11 opened 2 months ago by

When qwen3.6 omni??

#10 opened 3 months ago by

404 Not Found when trying to retrieve pre-compiled wheel

#9 opened 7 months ago by

vLLM serve for Qwen3-Omni currently only supports the thinker model.

#8 opened 10 months ago by

How much vram?

#7 opened 11 months ago by

quantizes

#6 opened 11 months ago by

🚀 Best Practices for Evaluating the Qwen3-Omni Model

#5 opened 11 months ago by

GUFF量化版本已發佈(INT8、FP16)

#4 opened 11 months ago by

量化版本已發佈(INT8+FP16)

#3 opened 11 months ago by

🔥🔥🔥测评视频

#2 opened 11 months ago by

Local Installation Video and Testing - Step by Step

#1 opened 11 months ago by