can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q8_0 · 9.4 GB · 16–23 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB34–51 tok/sRuns great
Q3_K_M4.4 GB29–43 tok/sRuns great
Q4_K_M5.4 GB25–37 tok/sRuns great
Q5_K_M6.3 GB22–33 tok/sRuns great
Q6_K7.2 GB19–29 tok/sRuns great
Q8_09.4 GB16–23 tok/sRuns great
FP1617.6 GB9–13 tok/sTight / slow

Ran Granite 4.2 8B on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →