can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (512GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 512.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Muse Glimmer 30B at FP16 · 55.7 GB · 14–20 tok/s on a Mac Studio M5 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB52–78 tok/sRuns great
Q3_K_M14.0 GB44–66 tok/sRuns great
Q4_K_M17.3 GB37–56 tok/sRuns great
Q5_K_M20.1 GB33–50 tok/sRuns great
Q6_K23.4 GB29–44 tok/sRuns great
Q8_029.6 GB24–36 tok/sRuns great
FP1655.7 GB14–20 tok/sRuns great

Ran Muse Glimmer 30B on a Mac Studio M5 Ultra (512GB)? Add your real numbers →