can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (64GB) run Llama 4 Scout (MoE)?

Llama · See model card · estimated for a 64.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Llama 4 Scout (MoE) at Q2_K · 39.6 GB · 53–79 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.6 GB53–79 tok/sTight / slow
Q3_K_M51.8 GB45–67 tok/sWon't fit
Q4_K_M65.4 GB38–57 tok/sWon't fit
Q5_K_M76.6 GB34–51 tok/sWon't fit
Q6_K88.4 GB30–45 tok/sWon't fit
Q8_0114.5 GB25–37 tok/sWon't fit
FP16215.6 GB14–21 tok/sWon't fit

Ran Llama 4 Scout (MoE) on a Mac Studio M1 Ultra (64GB)? Add your real numbers →