Can I run this LLM?
Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Qwen3.6 35B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 35B-A3B (MoE) at Q8_0 · 36.9 GB · 40–60 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.3 GB | 80–120 tok/s | Runs great |
| Q3_K_M | 16.6 GB | 68–103 tok/s | Runs great |
| Q4_K_M | 22.1 GB | 57–86 tok/s | Runs great |
| Q5_K_M | 26.5 GB | 51–77 tok/s | Runs great |
| Q6_K | 29.3 GB | 48–71 tok/s | Runs great |
| Q8_0 | 36.9 GB | 40–60 tok/s | Runs great |
| FP16 | 69.4 GB | 24–37 tok/s | Won't fit |
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3.6 35B-A3B (MoE) on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →