Hacker News new | ask | show | jobs
by coder543 29 days ago
> For a MBP I have 48 GB of RAM M5 Pro. It runs at about 12-14 t/s at Q4

Are you running with MTP enabled? I have seen some people on M5 hardware report 20+ t/s on Qwen3.6-27B using MTP... and I think that was a regular M5, not even M5 Pro.
1 comments
bitexploder 29 days ago
Nope. MLX in LMStudio. The simplest config with zero tuning effort.
link
coder543 29 days ago
Unsloth Studio is also very low effort, and a lot better than LM Studio in my opinion. (Performance, compatibility with Gemma 4, actually open source, etc.)
link