can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M5 Max (36GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Muse Glimmer 30B at Q5_K_M · 20.1 GB · 14–21 tok/s on a MacBook Pro M5 Max (36GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB24–36 tok/sRuns great
Q3_K_M14.0 GB20–29 tok/sRuns great
Q4_K_M17.3 GB16–24 tok/sRuns great
Q5_K_M20.1 GB14–21 tok/sRuns great
Q6_K23.4 GB12–18 tok/sTight / slow
Q8_029.6 GB10–15 tok/sWon't fit
FP1655.7 GB5–8 tok/sWon't fit

Ran Muse Glimmer 30B on a MacBook Pro M5 Max (36GB)? Add your real numbers →