can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (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 · 59–88 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB179–269 tok/sRuns great
Q3_K_M14.0 GB158–237 tok/sRuns great
Q4_K_M17.3 GB139–209 tok/sRuns great
Q5_K_M20.1 GB127–190 tok/sRuns great
Q6_K23.4 GB114–172 tok/sRuns great
Q8_029.6 GB97–145 tok/sRuns great
FP1655.7 GB59–88 tok/sRuns great

Ran Muse Glimmer 30B on a AMD Instinct MI300X (192GB)? Add your real numbers →