can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Ornith 1.0 9B?

Ornith · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.0 9B at Q8_0 · 9.5 GB · 16–23 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.6 GB24–36 tok/sRuns great
Q5_K_M6.5 GB22–32 tok/sRuns great
Q6_K7.4 GB19–29 tok/sRuns great
Q8_09.5 GB16–23 tok/sRuns great
FP1617.9 GB9–13 tok/sTight / slow

Ran Ornith 1.0 9B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →