can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M5 (32GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Muse Glimmer 30B at Q5_K_M · 19.2 GB · 5–8 tok/s on a MacBook Air/Pro M5 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q5_K_M19.2 GB5–8 tok/sTight / slow
Q8_029.6 GB3–5 tok/sWon't fit
FP1655.7 GB2–3 tok/sWon't fit

Ran Muse Glimmer 30B on a MacBook Air/Pro M5 (32GB)? Add your real numbers →