News for hackers. Stuff that matters.
Re:Experimenting with Local LLMs on macOS by data-ottawa on Tuesday September 09, 2025 @09:56AM (#45181976)
30-40 at 64k context, but it's a mixture of experts model.

A 70b dense model is slower

Qwen coder 30b Q4 runs 40+.

There are no comments on this comment yet.