How to run Qwen3.8-27B on a single 16GB card

autodidacts.io

1 pointCuriositry1 comment

Have you tried any vision tasks with this model? We've been serving these on our gateway [1], and the quants are quite terrible for vision. Curious to hear your experience.

[1] https://www.vlm.run/gateway

Reply on news.ycombinator.com