Resources

Add GPQA evaluation result

#20 opened 3 months ago by

merve

Add GPQA evaluation result

#19 opened 3 months ago by

merve

Request for SWE-bench-Verified Evaluation Metrics of Qwen3-Next-80B-A3B.

➕ 2

#18 opened 4 months ago by

ludybupt

希望能控制思考level

#17 opened 5 months ago by

hqhxzly

I hope qwen3 will open-source a large 120b model, like the GPT-120b. GPT's Chinese version isn't very good; we still need qwen.

👍 1

#16 opened 5 months ago by

mimeng1990

经典逻辑推理题无法给出正确答案

#15 opened 6 months ago by

pypry

FP8 版本无法使用vllm v0.10.2 来加载

#14 opened 7 months ago by

iwaitu

Good for Roleplay - Sucks at tool calling

#13 opened 7 months ago by

abiteddie

4 bit with bitsandbytes not working

#12 opened 7 months ago by

TheBigBlockPC

Fix broken qwen3-next blog link

#11 opened 7 months ago by

Smorty100

Something of with knowledge cutoff date?

#10 opened 7 months ago by

Nirav-Madhani

Failed to run VLLM batch inference

➕ 1

#9 opened 7 months ago by

Junxiao-Zhao

🚀 Best Practices for Evaluating the Qwen3-Next Model

🚀👍 7

#8 opened 7 months ago by

Yunxz

vllm: error: unrecognized arguments: --enable-reasoning

#7 opened 7 months ago by

evilll

awq

👍 8

#5 opened 7 months ago by

groxaxo

The Thinking model has a higher hallucination rate than the Instruct model and tends to overlook details in long contexts.

#4 opened 7 months ago by

xiaoxiao218

Local Installation Video and Testing On CPU - Step by Step

#3 opened 7 months ago by

fahdmirzac

Support of 1M context doubt

👀 1

#2 opened 7 months ago by

clyang33

GGUF when?

😎👍 14

#1 opened 7 months ago by

ouchiewouchie

Add GPQA evaluation result

Add GPQA evaluation result

Request for SWE-bench-Verified Evaluation Metrics of Qwen3-Next-80B-A3B.

希望能控制思考level

I hope qwen3 will open-source a large 120b model, like the GPT-120b. GPT's Chinese version isn't very good; we still need qwen.

经典逻辑推理题无法给出正确答案

FP8 版本无法使用vllm v0.10.2 来加载

Good for Roleplay - Sucks at tool calling

4 bit with bitsandbytes not working

Fix broken qwen3-next blog link

Something of with knowledge cutoff date?

Failed to run VLLM batch inference

🚀​​ Best Practices for Evaluating the Qwen3-Next Model

vllm: error: unrecognized arguments: --enable-reasoning

awq

The Thinking model has a higher hallucination rate than the Instruct model and tends to overlook details in long contexts.

Local Installation Video and Testing On CPU - Step by Step

Support of 1M context doubt

GGUF when?

🚀 Best Practices for Evaluating the Qwen3-Next Model