Paolo Rosson(@redp314):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 👇

Paolo Rosson

@redp314

Head of Applied AI at Dext. Building | Quantum physics PhD from Oxford | Former Italian blindfolded Rubik’s cube record holder

参加 May 2015

2.3K フォロー中 1.7K ファン

Paolo Rosson@redp314

2026.08.10 21:41

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 👇