can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Pro (64GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Muse Glimmer 30B at Q3_K_M · 14.0 GB · 14–20 tok/s on a MacBook Pro M5 Pro (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB17–25 tok/sRuns great
Q3_K_M14.0 GB14–20 tok/sRuns great
Q4_K_M17.3 GB11–17 tok/sTight / slow
Q5_K_M20.1 GB10–14 tok/sTight / slow
Q6_K23.4 GB8–13 tok/sTight / slow
Q8_029.6 GB7–10 tok/sTight / slow
FP1655.7 GB4–5 tok/sWon't fit

Ran Muse Glimmer 30B on a MacBook Pro M5 Pro (64GB)? Add your real numbers →