Qwen/Qwen3-235B-A22B · Discussions

#34 opened 1 day ago by

jujutechnology

关于Qwen3-235B-A22B在文学创作中“思维链”模式对输出风格影响的观察与建议

8

#33 opened 7 days ago by

yxcl6874

In complex reasoning tasks Qwen3 is far behind QwQ

12

#32 opened 8 days ago by

AdamF92

I know not related but saw This Star Wars picture on Facebook and i thought it is code so trying to say Hi to Someone named John!

#31 opened 8 days ago by

Not sure Clocks keep coming up and keep getting the run around might need time stamping confirmations?

#30 opened 9 days ago by

Not Sure Orginal to Persian to Binary?

#29 opened 9 days ago by

Qwen3 is simply amazing.

#28 opened 9 days ago by

Trilogix1

Upload b891b3c3bb6a146a8e809bb72a06d101.png

#27 opened 10 days ago by

Jalil16

Add image visual recognition output just like qwen 2.5 vl-32b instruct

6

#26 opened 10 days ago by

devopsML

English to French - French to English based on Meta & HuggingFace Chat Bot

#25 opened 12 days ago by

Qwen3 幻觉太高了，比 Qwen 2.5 差太多了

9

#24 opened 13 days ago by

hehua2008

Upload 3 files

#23 opened 14 days ago by

neuroQuantu

Upload 3 files

#22 opened 14 days ago by

neuroQuantu

Model keeps talking about Cumhurbaşkanlığı Sarayı when speaking Turkish

#21 opened 14 days ago by

aeminkocal

Qwen3 not Using Tools in Complex Prompts Unlike QwQ-32B

8

#20 opened 15 days ago by

Anaudia

Thanks a lot for this release

#19 opened 15 days ago by

Volko76

Does anyone feel Qwen3 often fails to follow instructions accurately?

7

#18 opened 15 days ago by

DOFOFFICIAL

Two of the base models are missing

#17 opened 16 days ago by

ZhangRC

Qwen is loosing broad knowledge since Qwen2.

10

14

#16 opened 16 days ago by

phil111

GPQA perf for DSV3-Base seems wrong

#15 opened 16 days ago by

AChen-qaq

About the non-thinking mode

#14 opened 16 days ago by

volcanos

72B-MoE

#13 opened 16 days ago by

avalonsec

235B会放出来Base模型吗？

6

#12 opened 16 days ago by

Yantao2009

看模型介绍和模型结构里面没有关于vision encoder的部分，但是在qwen的在线模型服务界面可以用这个模型去看图片，想问下视觉部分是复用了哪个vision encoder呢？

#11 opened 16 days ago by

Chloez

有用4张H20实践过的大佬吗

#10 opened 16 days ago by

Edison0902

8张80G显存的8卡A100能部署不？

9

#9 opened 16 days ago by

Yuxin362

User rating and reviews of Qwen3 App and Qwen3 Model

#8 opened 16 days ago by

DeepNLP

是不是奖励函数没有ngram重复度惩罚

#7 opened 16 days ago by

wzx111

🚀[Fine-tuning] Qwen3-MoE Megatron Training Implementation and Best Practices👋

5

#6 opened 16 days ago by

study-hjt

【Evaluation】Best practice for evaluating Qwen3 !!

#5 opened 16 days ago by

wangxingjun778

Please upload the base model for this one

6

#4 opened 16 days ago by

mesh-ops

GPTQ/AWQ

12