It is much faster though. On my m1 max, describing a picture (quick way to get a... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		spwa4 40 days ago \| parent \| context \| favorite \| on: Qwen3.6-35B-A3B on my laptop drew me a better peli... It is much faster though. On my m1 max, describing a picture (quick way to get a pretty large context): Qwen 3.6 35b a3b: 34 tok/sec Qwen 3.5 27b: 10 tok/sec Qwen 3.5 35b a3b: doesn't support image input

upboundspiral 40 days ago | [–]

I've been using Qwen 3.5 35B-A3B with images as input so I suspect you perhaps didn't include the vision part of the model during testing (I use llama.cpp and I learned I needed to include the separate mmproj part).

m-emre 38 days ago | [–]

What is the quantization level of your Owen 3.6 3b model?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact