rreinold2

Joined 1 month ago

Karma

1

Submissions

3

Member since

Sep 23

View on Hacker News

Recent submissions

Comment · 1 month ago

Guideline is (TOTAL_RAM - 5GB overhead) = max size, in billions of parameters. So 16 - 5 = 11, so <11B. Qwen 3.8 9B is a good fit

Jev-serve: Run latest qwen3.8, all LLM models, mlx-supported github.com

2 rreinold2 1 month ago 2 comments