can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Llama 4 Scout (MoE)?

Llama · See model card · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 4 Scout (MoE) at Q5_K_M · 76.6 GB · 12–19 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.6 GB21–32 tok/sRuns great
Q3_K_M51.8 GB17–26 tok/sRuns great
Q4_K_M65.4 GB14–21 tok/sRuns great
Q5_K_M76.6 GB12–19 tok/sRuns great
Q6_K88.4 GB11–16 tok/sWon't fit
Q8_0114.5 GB9–13 tok/sWon't fit
FP16215.6 GB5–7 tok/sWon't fit

Ran Llama 4 Scout (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →