can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Ornith 1.5 9B?

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

Yes — it runs great.

Best fit: Ornith 1.5 9B at Q8_0 · 9.6 GB · 16–24 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB33–50 tok/sRuns great
Q3_K_M4.9 GB28–43 tok/sRuns great
Q4_K_M5.9 GB24–37 tok/sRuns great
Q5_K_M6.9 GB22–32 tok/sRuns great
Q6_K7.7 GB20–29 tok/sRuns great
Q8_09.6 GB16–24 tok/sRuns great
FP1617.9 GB9–14 tok/sTight / slow

Ran Ornith 1.5 9B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →