09-02-2026, 05:01 PM
Did a bit of testing and thought I'd post the result here.
I tried this with Gemma using vLLM on dual 3090. The headline result was better than I expected, but quant drift still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
I tried this with Gemma using vLLM on dual 3090. The headline result was better than I expected, but quant drift still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
learning in public