How we got this number
Each generated token reads the whole model from memory once: 1.4 GB. The Mac mini M4 (16GB) moves 120 GB/s, so the ceiling is 86 tokens/sec. Real machines reach a fraction of that ceiling; we use 80%, calibrated against a measured Mac run. 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 Mac mini M4 (16GB)
| Qwen3.5 0.8B | Fast | 96 tok/s |
| DeepSeek-R1 1.5B | Fast | 87 tok/s |
| Qwen 1.8B | Fast | 87 tok/s |
| Llama 3.2 1B | Fast | 74 tok/s |
| Qwen 3 1.7B | Fast | 69 tok/s |
| minicpm v4.6 1B | Fast | 60 tok/s |