How we got this number
Each generated token reads the whole model from memory once: 80 GB. The Mac mini M5 Pro (24GB) moves 307 GB/s, so the ceiling is 3.8 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 medium 3.5 128B
| Mac Studio M5 Ultra (256GB) | 12 tok/s | Check price → |
| Mac Studio M5 Ultra (96GB) | 7.4 tok/s | Check price → |
| NVIDIA DGX Spark (128GB) | 2.4 tok/s | Check price → |
| Ryzen AI Max+ 395 mini PC (128GB) | 2.2 tok/s | Check price → |
Other models on the Mac mini M5 Pro (24GB)
| Qwen 3 30B (A3B) | Fast | 43 tok/s |
| Qwen3 Coder 30B (A3B) | Fast | 43 tok/s |
| Gemma 4 26B (A4B) | Fast | 29 tok/s |
| Granite 4.1 30B | Usable, but slow | 8.7 tok/s |
| Gemma 3 27B | Usable, but slow | 8.7 tok/s |
| Qwen3.5 27B | Usable, but slow | 8.7 tok/s |