can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (512GB) run Step 3.7 Flash (MoE)?

Step · Apache 2.0 · estimated for a 512.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Step 3.7 Flash (MoE) at Q8_0 · 212.0 GB · 36–55 tok/s on a Mac Studio M3 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K71.2 GB74–112 tok/sRuns great
Q3_K_M91.8 GB65–97 tok/sRuns great
Q4_K_M121.6 GB54–81 tok/sRuns great
Q5_K_M142.0 GB49–73 tok/sRuns great
Q6_K171.8 GB43–64 tok/sRuns great
Q8_0212.0 GB36–55 tok/sRuns great

Ran Step 3.7 Flash (MoE) on a Mac Studio M3 Ultra (512GB)? Add your real numbers →