Can I run this LLM?
Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Llama 3.2 1B?
Llama · Llama 3.2 Community · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.2 1B at FP16 · 2.5 GB · 48–72 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q4_K_M | 0.8 GB | 91–137 tok/s | Runs great |
| Q5_K_M | 0.9 GB | 85–128 tok/s | Runs great |
| Q6_K | 1.0 GB | 80–120 tok/s | Runs great |
| Q8_0 | 1.3 GB | 70–105 tok/s | Runs great |
| FP16 | 2.5 GB | 48–72 tok/s | Runs great |
Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runsLlama 3.2 1B on other machinesWhat to buy to run it →
Ran Llama 3.2 1B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →