can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Muse Glimmer 30B?

Muse · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Muse Glimmer 30B at Q2_K · 11.0 GB · 14–21 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.0 GB14–21 tok/sRuns great
Q3_K_M14.0 GB11–17 tok/sTight / slow
Q4_K_M17.3 GB9–14 tok/sTight / slow
Q5_K_M20.1 GB8–12 tok/sTight / slow
Q6_K23.4 GB7–11 tok/sTight / slow
Q8_029.6 GB6–8 tok/sTight / slow
FP1655.7 GB3–5 tok/sTight / slow
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runsMuse Glimmer 30B on other machinesWhat to buy to run it →

Ran Muse Glimmer 30B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →