How we got this number
Each generated token reads the active part of the model from memory once: 2.9 GB. The Ryzen AI Max+ 395 mini PC (128GB) moves 256 GB/s, so the ceiling is 88 tokens/sec. Real machines reach a fraction of that ceiling; we use 70%, an assumption until we get measured runs for this kind of machine. Send us your real numbers and we'll replace the estimate.
Faster machines for Gemma 4 26B (A4B)
Other models on the Ryzen AI Max+ 395 mini PC (128GB)
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| Qwen 3 30B (A3B) | Fast | 52 tok/s |
| Qwen3 Coder 30B (A3B) | Fast | 52 tok/s |
| Qwen 3-VL 30B (A3B) | Fast | 50 tok/s |
| Llama 2 7B | Fast | 47 tok/s |
| Code Llama 7B | Fast | 47 tok/s |