Can I run this LLM?
Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run GLM-4 9B?
GLM · MIT · estimated for a 64.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-4 9B at Q8_0 · 10.0 GB · 15–23 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 4.0 GB | 33–50 tok/s | Runs great |
| Q3_K_M | 5.0 GB | 28–42 tok/s | Runs great |
| Q4_K_M | 6.2 GB | 24–35 tok/s | Runs great |
| Q5_K_M | 7.1 GB | 21–31 tok/s | Runs great |
| Q6_K | 8.3 GB | 18–27 tok/s | Runs great |
| Q8_0 | 10.0 GB | 15–23 tok/s | Runs great |
| FP16 | 18.8 GB | 9–13 tok/s | Tight / slow |
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) runsGLM-4 9B on other machinesWhat to buy to run it →
Ran GLM-4 9B on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →