Re:Accelerating Gemma 4: faster inference with multi-token p...
by mcv on Tuesday May 05, 2026 @05:50PM
(#48029115)
One of the consequences of Gemma's speed is that you can run it on a GPU that's technically too small for it. I've run it on my 4070, and while the output wasn't blazingly fast, it was usable. (Though I haven't used it for anything complex yet. I'm sure that will be different.)
[ Parent
| on HN ]
There are no comments on this comment yet.