Can I run this LLM?
Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Qwen3.5 9B?
Qwen · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.5 9B at Q8_0 · 9.5 GB · 16–23 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 3.9 GB | 32–48 tok/s | Runs great |
| Q4_K_M | 5.4 GB | 25–37 tok/s | Runs great |
| Q5_K_M | 6.4 GB | 22–33 tok/s | Runs great |
| Q6_K | 7.4 GB | 19–29 tok/s | Runs great |
| Q8_0 | 9.5 GB | 16–23 tok/s | Runs great |
| FP16 | 17.9 GB | 9–13 tok/s | Tight / slow |
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runsQwen3.5 9B on other machinesWhat to buy to run it →
Ran Qwen3.5 9B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →