can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M5 Ultra (96GB) run Llama 4 Scout (MoE)?

Llama · See model card · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 4 Scout (MoE) at Q3_K_M · 51.8 GB · 60–90 tok/s on a Mac Studio M5 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.6 GB70–105 tok/sRuns great
Q3_K_M51.8 GB60–90 tok/sRuns great
Q4_K_M65.4 GB52–78 tok/sTight / slow
Q5_K_M76.6 GB47–70 tok/sWon't fit
Q6_K88.4 GB42–63 tok/sWon't fit
Q8_0114.5 GB35–52 tok/sWon't fit
FP16215.6 GB21–31 tok/sWon't fit

Ran Llama 4 Scout (MoE) on a Mac Studio M5 Ultra (96GB)? Add your real numbers →