Qwen
/

QwQ-32B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (2)

Thanks a lot for sharing this model!

#26 opened about 1 hour ago by

Doesn't Generate `<think>` tags

#25 opened about 1 hour ago by

【乱码问题】输入约1w长度，输出超过1000长度，结尾部分会乱码。稳定复现！

#24 opened about 1 hour ago by

是否需要添加系统prompt

#23 opened about 2 hours ago by

A pure C++ high-performance OpenAI LLM service powered by TensorRT-LLM and GRPS, with support for QWQ.

#22 opened about 2 hours ago by

复杂推理进入死循环

#21 opened about 4 hours ago by

I've tried it, the locally deployed 8G4060 can run, it's just a bit slower.

#20 opened about 5 hours ago by

When will you fix the model replies missing</think>\n start tags

#19 opened about 6 hours ago by

Update QwQ collection

#18 opened about 8 hours ago by

Off the charts - GREAT JOB!

#17 opened about 8 hours ago by

Where can I see the GPQA for this model?

#16 opened about 8 hours ago by

issue of "think too much" ，how to？(chinese)

#14 opened about 11 hours ago by

Local Installation Video - Step-by-Step Tutorial

#13 opened about 13 hours ago by

Tool-Calling Format

#12 opened about 13 hours ago by

我的3090TI 24GB显存运行非常愉快！感谢开发团队！

#11 opened about 13 hours ago by

add missing special tokens in tokenizer.json

#10 opened about 13 hours ago by

Is `rms_norm_eps` 1e-5 or 1e-6

#9 opened about 13 hours ago by

Oh My NVDA Position

#8 opened about 13 hours ago by

What languages were you trained in?

#7 opened about 14 hours ago by

You guys are the pioneers!

#6 opened about 14 hours ago by

recommended generation parameters

#5 opened about 14 hours ago by

missing opening <think>

#4 opened about 15 hours ago by

One Of Many

#3 opened about 15 hours ago by

Is system prompt required?

#2 opened about 16 hours ago by