can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M2 Ultra (192GB) run Mistral Small 4 119B (MoE)?

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

Yes — it runs great.

Best fit: Mistral Small 4 119B (MoE) at Q6_K · 99.4 GB · 62–93 tok/s on a Mac Studio M2 Ultra (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.4 GB86–129 tok/sRuns great
Q4_K_M73.8 GB73–110 tok/sRuns great
Q5_K_M89.2 GB66–99 tok/sRuns great
Q6_K99.4 GB62–93 tok/sRuns great
Q8_0126.5 GB53–79 tok/sTight / slow
FP16238.0 GB33–50 tok/sWon't fit

Ran Mistral Small 4 119B (MoE) on a Mac Studio M2 Ultra (192GB)? Add your real numbers →