Qwen/Qwen3.5-9B · Discussions

有没有直接用transformer库的用法示例？

#49 opened about 7 hours ago by

tangjiuqi097

fix chat template to avoid empty historical `<think>` blocks

#48 opened about 24 hours ago by

latent-variable

Can we have a FP8 version?

👍 2

1

#47 opened 3 days ago by

drguolai

Upload generation_config.json

#46 opened 3 days ago by

Manojkumar96

finetuning

#45 opened 9 days ago by

huu-ontocord

Update README.md

#44 opened 10 days ago by

IFthisisrealitynbds

Delete README.md

#43 opened 11 days ago by

Maniche23

Will ai completely replace humans

#42 opened 12 days ago by

okateun

Create 123

#41 opened 13 days ago by

Alex-Neural

Proposal: new chat_template_arg `enable_history_reasoning` for reusing prompt cache among querys within Agents .

#39 opened 17 days ago by

Abioy

Add ScreenSpot-Pro evaluation result

#37 opened 22 days ago by

merve

Add MathArena evaluation result for hmmt/hmmt_feb_2026

#36 opened 23 days ago by

JasperDekoninck

Add MathArena evaluation result for aime/aime_2026

#35 opened 23 days ago by

JasperDekoninck

Is the Qwen3VL inference guide applicable to Qwen3.5?

#34 opened 25 days ago by

summerishere

Create generation_config.json

#32 opened 30 days ago by

jalola

nobody

2

#31 opened about 1 month ago by

Miggyjp

Install & run Qwen/Qwen3.5-9B easily using llmpm

1

#30 opened about 1 month ago by

sarthak-saxena

anuoluwapo

#28 opened about 1 month ago by

mapema

for the love of action model

3

#27 opened about 1 month ago by

sirmyy

Just asking

#26 opened about 1 month ago by

levuci88

greeting

1

#25 opened about 1 month ago by

ahmafc123

kamote

1

#24 opened about 1 month ago by

balatubs123

ilhmop09

🔥 1

2

#23 opened about 1 month ago by

cryptosxion

Update README.md

#22 opened about 1 month ago by

cryptosxion

mr clean

1

#21 opened about 1 month ago by

ghetra

Running the model using HF backend

#20 opened about 1 month ago by

sahilj2701

life as a journey

2

#19 opened about 1 month ago by

bdfsparkles

trying

#18 opened about 1 month ago by

youngbyuu

Update README.md

1

#17 opened about 1 month ago by

kerasakit

possible to run on RTX 2060 8GB + 32GB RAM DDR4?

4

#16 opened about 1 month ago by

krigeta

No generation_config.json?

➕ 2

#15 opened about 1 month ago by

deep1401

Now we waiting for Qwen4-10B

3

#14 opened about 1 month ago by

Naster17

How to disable or reduce thinking

2

#13 opened about 1 month ago by

AyoubChLin

Giberish response when using the model with transformers library with an image

4

#12 opened about 1 month ago by

jluixjurado

Can‘t run AutoModelForSequenceClassification for Qwen3.5-9B

1

#11 opened about 1 month ago by

HanyuYuzuru

Tool call stops in middle of the conversation, doesn't finish the complete task

👍 3

2

#10 opened about 1 month ago by

TechCarbasa

How to reproduce the results of Android World?

#9 opened about 1 month ago by

llmmlman

how does it perform on SWE-Bench or in general for agentic coding

👀 3

#7 opened about 1 month ago by

mayankiit04

Installation Video and Testing - Step by Step

#6 opened about 1 month ago by

fahdmirzac

Can we get a 9B-FP8 version next

👍 14

4

#5 opened about 1 month ago by

kq

DGX SPARK VLLM RESULTS

👍 2

2

#4 opened about 1 month ago by

RGMC98

value error, The checkpoint you are trying to load has model type `qwen3_5`

3

#3 opened about 1 month ago by

cesinsingapore

Add GPQA Diamond evaluation result

#2 opened about 1 month ago by

SaylorTwift

new soto for dense

👍🧠 4

#1 opened about 1 month ago by

ox-ox