can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3090 (24GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Muse Glimmer 30B at Q5_K_M · 19.8 GB · 31–47 tok/s on a NVIDIA RTX 3090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q5_K_M19.8 GB31–47 tok/sTight / slow
Q8_029.6 GB22–33 tok/sWon't fit
FP1655.7 GB12–18 tok/sWon't fit

Ran Muse Glimmer 30B on a NVIDIA RTX 3090 (24GB)? Add your real numbers →