can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Muse Glimmer 30B at FP16 · 55.7 GB · 22–33 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB90–134 tok/sRuns great
Q3_K_M14.0 GB75–112 tok/sRuns great
Q4_K_M17.3 GB63–94 tok/sRuns great
Q5_K_M20.1 GB55–83 tok/sRuns great
Q6_K23.4 GB49–73 tok/sRuns great
Q8_029.6 GB40–60 tok/sRuns great
FP1655.7 GB22–33 tok/sRuns great

Ran Muse Glimmer 30B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →