zlacker

[parent] [thread] 0 comments
1. mark_l+(OP)[view] [source] 2026-02-04 16:38:58
A 3B resident parameter MOE allows absolutely huge savings on inference costs. I use a cloud provider for models to large to run locally, can’t wit for them to support qwen3-coder-next hopefully in a few days.

So much expensive inference is provided free or at large discounts - that craziness should end.

[go to top]