OpenVINO
/

Qwen3.8-27B-int8-ov

Image-Text-to-Text

Model card Files Files and versions

Resources

View closed (1)

Model context is limited to ~120k when running on iGPU

#5 opened 5 days ago by

Why no MTP for the int8 version

#4 opened 12 days ago by

Any bios tweaks to improve inference performance?

#3 opened 15 days ago by

Unable to start

#2 opened 16 days ago by