Jev-serve: Run latest qwen3.8, other frozen LLM models, mlx-supported (github.com) 1 points by rreinold2 2d ago ↗ HN
[–] allensallinger 1d ago ↗ Any recommendations for which of the models to try on macs with 16 GB of mem, and is this running well with any of the smaller models? [–] rreinold2 20h 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
[–] rreinold2 20h 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
3 comments
[ 0.30 ms ] story [ 18.7 ms ] thread