can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA B200 (192GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Muse Glimmer 30B at FP16 · 55.7 GB · 82–123 tok/s on a NVIDIA B200 (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB217–325 tok/sRuns great
Q3_K_M14.0 GB196–293 tok/sRuns great
Q4_K_M17.3 GB176–264 tok/sRuns great
Q5_K_M20.1 GB163–244 tok/sRuns great
Q6_K23.4 GB149–224 tok/sRuns great
Q8_029.6 GB129–193 tok/sRuns great
FP1655.7 GB82–123 tok/sRuns great

Ran Muse Glimmer 30B on a NVIDIA B200 (192GB)? Add your real numbers →