Paolo Rosson
@redp314
Head of Applied AI at Dext. Building | Quantum physics PhD from Oxford | Former Italian blindfolded Rubikโs cube record holder
๊ฐ์
May 2015
2.3K ํ๋ก์ ์ค 1.7K ํฌ
Got Meta's new Muse Glimmer 30B running on my MacBook (M3 Max, 96GG) and tested the serving options available so far.
Fastest right now: Ollama's MLX engine (DFlash included) at ~29 tok/s.
Tuned llama.cpp: ~21. Raw mlx-vlm: ~10, not optimized yet.
Numbers below if you're setting it up ๐
๋ ๋ณด๊ธฐ
