News for hackers. Stuff that matters.

A comment on Qwen2.5-VL-32B: Smarter and Lighter. Parent comment

Re:Qwen2.5-VL-32B: Smarter and Lighter by unquietwiki on Monday March 24, 2025 @03:45PM (#43464718)
I'm using open-webui at home with a couple of different models. gemma2-9b fits in VRAM on a NV 3060 card + performs nicely.
[ Parent | on HN ]
Re:Qwen2.5-VL-32B: Smarter and Lighter by zakki on Monday March 24, 2025 @05:30PM (#43465594)
What is the memory of your NV3060? 8GB?
[ Parent | on HN ]
Re:Qwen2.5-VL-32B: Smarter and Lighter by ngvjmfgb on Monday March 24, 2025 @06:53PM (#43466243)
12GB (edit: that is what mine is)
[ Parent | on HN ]
Re:Qwen2.5-VL-32B: Smarter and Lighter by mdp2021 on Tuesday March 25, 2025 @05:21AM (#43469350)
> performs nicely

Do you have rough indication of token/s ?

[ Parent | on HN ]