How we got this number
Each generated token reads the whole model from memory once: 15 GB. The Mac mini M2 (16GB) moves 100 GB/s, so the ceiling is 6.7 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 Mistral small3.2 24B
| Mac Studio M5 Ultra (96GB) | 66 tok/s | Check price → |
| Mac Studio M5 Ultra (256GB) | 66 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 33 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 16 tok/s | Check price → |
Other models on the Mac mini M2 (16GB)
| lfm 2.5 8B (A1B) | Fast | 65 tok/s |
| Qwen2.5-VL 3B | Fast | 25 tok/s |
| Gemma 3 4B | Fast | 24 tok/s |
| Qwen 3-VL 4B | Fast | 24 tok/s |
| translateGemma 4B | Fast | 24 tok/s |
| Qwen3.5 4B | Fast | 24 tok/s |