can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Laguna S 2.1 (MoE)?

Laguna · openmdw-1.1 · estimated for a 64.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Laguna S 2.1 (MoE) at Q2_K · 39.7 GB · 43–65 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.7 GB43–65 tok/sTight / slow
Q3_K_M54.0 GB35–52 tok/sWon't fit
Q4_K_M73.1 GB28–41 tok/sWon't fit
Q5_K_M87.9 GB24–36 tok/sWon't fit
Q6_K97.9 GB22–33 tok/sWon't fit
Q8_0125.0 GB18–26 tok/sWon't fit
FP16235.2 GB10–15 tok/sWon't fit
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) runsLaguna S 2.1 (MoE) on other machinesWhat to buy to run it →

Ran Laguna S 2.1 (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →