Qwen
/

Qwen3.5-0.8B

Image-Text-to-Text

Model card Files Files and versions

Resources

View closed (1)

0.8B with mtp is slower than without mtp

#15 opened 7 days ago by

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

#14 opened 8 days ago by

latent-variable

When vllm deployment is started using mtp config, an error will be reported. Please help！

#13 opened 13 days ago by

anis

#12 opened 28 days ago by

Add ScreenSpot-Pro evaluation result

#11 opened 29 days ago by

How to change the model to ONNX format

#9 opened about 1 month ago by

Can I run this on the macbook apple Silicon?

#8 opened about 1 month ago by

Request format for transformers serve for Qwen3.5

#7 opened about 1 month ago by

Is there a comparison between Qwen3.5-0.8B and Qwen3-0.6B?

#6 opened about 1 month ago by

Can I run these models on google collab ? Please Help!!

#5 opened about 1 month ago by

Could someone make Qwen/Qwen3.5-0.4B?

#4 opened about 1 month ago by

Will there be embedding only versions of these models?

#3 opened about 1 month ago by

Installation Video and Testing - Step by Step

#2 opened about 1 month ago by

Add MMLU-Pro evaluation result

#1 opened about 1 month ago by