Can I run this LLM?
Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Gemma 4 12B?
Gemma · Apache 2.0 · estimated for a 64.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 12B at Q8_0 · 12.7 GB · 12–18 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 5.7 GB | 24–36 tok/s | Runs great |
| Q4_K_M | 7.1 GB | 20–30 tok/s | Runs great |
| Q5_K_M | 8.4 GB | 18–26 tok/s | Runs great |
| Q6_K | 9.8 GB | 15–23 tok/s | Runs great |
| Q8_0 | 12.7 GB | 12–18 tok/s | Runs great |
| FP16 | 23.8 GB | 7–10 tok/s | Tight / slow |
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) runsGemma 4 12B on other machinesWhat to buy to run it →
Ran Gemma 4 12B on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →