How we got this number
Each generated token reads the whole model from memory once: 1.4 GB. The Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) moves 89.6 GB/s, so the ceiling is 64 tokens/sec. Real machines reach a fraction of that ceiling; we use 60%, 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 Granite 3.1 moe 1B
| Mac mini M5 Pro (24GB) | 120+ tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 120+ tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 120+ tok/s | Check price → |
| Mac Studio M5 Ultra (96GB) | 120+ tok/s | Check price → |
Other models on the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)
| Qwen3.5 0.8B | Fast | 54 tok/s |
| DeepSeek-R1 1.5B | Fast | 49 tok/s |
| Qwen 1.8B | Fast | 49 tok/s |
| Llama 3.2 1B | Fast | 41 tok/s |
| Qwen 3 1.7B | Fast | 38 tok/s |
| minicpm v4.6 1B | Fast | 34 tok/s |