can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at Q8_0 · 37.8 GB · 40–60 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB78–118 tok/sRuns great
Q3_K_M16.7 GB69–103 tok/sRuns great
Q4_K_M21.9 GB59–88 tok/sRuns great
Q5_K_M25.5 GB53–80 tok/sRuns great
Q6_K30.5 GB47–70 tok/sRuns great
Q8_037.8 GB40–60 tok/sRuns great
FP1671.1 GB24–36 tok/sWon't fit

Ran Ornith 1.5 35B-A3B (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →