can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Granite 4.2 30B?

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

Yes — it runs great.

Best fit: Granite 4.2 30B at Q2_K · 10.9 GB · 13–20 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB13–20 tok/sRuns great
Q3_K_M14.1 GB11–16 tok/sTight / slow
Q4_K_M17.7 GB9–13 tok/sTight / slow
Q5_K_M20.8 GB8–11 tok/sTight / slow
Q6_K24.0 GB7–10 tok/sTight / slow
Q8_031.1 GB5–8 tok/sTight / slow
FP1658.6 GB3–4 tok/sTight / slow

Ran Granite 4.2 30B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →