can-i-run-this-llm

Can I run this LLM?

Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Qwen3 Coder Next 80B-A3B (MoE)?

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

Yes — it runs great.

Best fit: Qwen3 Coder Next 80B-A3B (MoE) at Q6_K · 65.8 GB · 44–67 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K29.2 GB69–103 tok/sRuns great
Q3_K_M38.3 GB61–91 tok/sRuns great
Q4_K_M49.3 GB53–79 tok/sRuns great
Q5_K_M59.2 GB47–71 tok/sRuns great
Q6_K65.8 GB44–67 tok/sRuns great
Q8_084.8 GB38–56 tok/sTight / slow
FP16159.5 GB23–35 tok/sWon't fit

Ran Qwen3 Coder Next 80B-A3B (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →