can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Llama 3.2 1B?

Llama · Llama 3.2 Community · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.2 1B at FP16 · 2.5 GB · 48–72 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.8 GB91–137 tok/sRuns great
Q5_K_M0.9 GB85–128 tok/sRuns great
Q6_K1.0 GB80–120 tok/sRuns great
Q8_01.3 GB70–105 tok/sRuns great
FP162.5 GB48–72 tok/sRuns great

Ran Llama 3.2 1B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →