can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run North Mini Code 1.0 (MoE)?

North · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: North Mini Code 1.0 (MoE) at Q8_0 · 32.4 GB · 37–56 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.5 GB71–106 tok/sRuns great
Q3_K_M14.2 GB61–92 tok/sRuns great
Q4_K_M19.2 GB52–78 tok/sRuns great
Q5_K_M23.0 GB47–70 tok/sRuns great
Q6_K25.5 GB44–66 tok/sRuns great
Q8_032.4 GB37–56 tok/sRuns great
FP1661.0 GB23–35 tok/sWon't fit

Ran North Mini Code 1.0 (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →