can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (128GB) run Step 3.7 Flash (MoE)?

Step · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Step 3.7 Flash (MoE) at Q2_K · 71.2 GB · 73–110 tok/s on a Mac Studio M1 Ultra (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K71.2 GB73–110 tok/sRuns great
Q3_K_M91.8 GB64–95 tok/sWon't fit
Q4_K_M121.6 GB53–80 tok/sWon't fit
Q5_K_M142.0 GB48–72 tok/sWon't fit
Q6_K171.8 GB42–63 tok/sWon't fit
Q8_0212.0 GB36–54 tok/sWon't fit

Ran Step 3.7 Flash (MoE) on a Mac Studio M1 Ultra (128GB)? Add your real numbers →