Qwen/Qwen3-30B-A3B · Discussions

Install & run Qwen/Qwen3-30B-A3B easily using llmpm

#41 opened about 1 month ago by

sarthak-saxena

good command to serving vllm Qwen/Qwen3-30B-A3B?

👍 1

#40 opened 4 months ago by

PYTHON01100100

I encountered the error: vllm: error: unrecognized arguments: --enable-reasoning

#39 opened 8 months ago by

HarleyWang

I got Qwen to "evolve" beyond it's core programming.

1

#38 opened 9 months ago by

Koitenshin

When new version?

👍 1

1

#37 opened 9 months ago by

MajinAnix

model-download

#36 opened 9 months ago by

Vaishnavi-Garad

add AIBOM

#35 opened 10 months ago by

fatima113

How to train the Qwen3-30B-A3B using Reinforcement Learning?

#34 opened 10 months ago by

alanayu

Add assistant mask support to Qwen3-30B-A3B

#33 opened 10 months ago by

waleko

There are something look like bugs.

🔥 1

#32 opened 11 months ago by

Jim-202020

Missing license file?

#31 opened 11 months ago by

cpwan9086

Over thinking. take too long time to produce final answer to some question.

2

#30 opened 11 months ago by

rosspanda0

how can I train a model if it uses a unique tokenizer?

#29 opened 11 months ago by

Veterse

Why does this problem "KeyError: 'qwen3_moe'" still occur after I update the transformers to 4.51.3

1

#28 opened 11 months ago by

Eureka9302

Why not distinguish between sequence_length equal to 1 and greater than 1 in the MoE module's forward function?

#27 opened 11 months ago by

nifeng154

asd-Qwen3-30B-A3B

#25 opened 11 months ago by

Axdar

Many experts seem to be underutilized, possible optimization potential.

#24 opened 11 months ago by

Dampfinchen

repetition

➕ 4

6

#23 opened 11 months ago by

Dampfinchen

Qwen3-30B-A3B

#22 opened 11 months ago by

FinitusEst

awq

#21 opened 11 months ago by

MrDragonFox

qwen3-30B

#20 opened 11 months ago by

xiaohuihehe

Comparing Qwen3-30B-A3B and Phi-4-mini-reasoning

🚀 1

#19 opened 12 months ago by

gptlocalhost

Qwen3 is great, but could be better.

👍 9

25

#18 opened 12 months ago by

phil111

Collections of Bad Cases User Reviews and Comments of Qwen3 30B A3B.

#17 opened 12 months ago by

DeepNLP

Doploy to Sagemaker error

#16 opened 12 months ago by

Hanyu1023

Enabling or disabling reasoning on-demand with remote vLLM server?

1

#15 opened 12 months ago by

abhinavkulkarni

asd-qwen1

#14 opened 12 months ago by

Axdar

Minor changes, big gains -- Huggingface MoE modeling enhancement

👍👀 5

3

#13 opened 12 months ago by

xiaowei4ai

AWQ quantized model support timeline?

👍 8

2

#12 opened 12 months ago by

hyunw55

image support

🧠👀 12

9

#9 opened 12 months ago by

kuliev-vitaly

Waiting for the Qwen3-VL

👀 17

8

#8 opened 12 months ago by

Maverick17

Very fast and powerful, but with one glaring weakness.

👍 1

2

#6 opened 12 months ago by

phil111

MoE question

🤯 9

4

#5 opened 12 months ago by

bojan2501

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

🚀 4

#3 opened 12 months ago by

study-hjt

【Evaluation】Best practice for evaluating Qwen3 !!

🔥👍 7

1

#2 opened 12 months ago by

wangxingjun778

Add languages tag

#1 opened 12 months ago by

de-francophones