How we got this number
Each generated token reads the whole model from memory once: 80 GB. The Mac Studio M5 Ultra (96GB) moves 1228.8 GB/s, so the ceiling is 15 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 → |
| 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 Studio M5 Ultra (96GB)
| Nemotron 3.5 lightning 30B (A3B) | Fast | 120+ tok/s |
| Qwen 3 30B (A3B) | Fast | 120+ tok/s |
| Gemma 4 26B (A4B) | Fast | 120+ tok/s |
| Qwen3.5 35B (A3B) | Fast | 120+ tok/s |
| gpt-oss 120B | Fast | 120+ tok/s |
| Qwen3 Coder 30B (A3B) | Fast | 120+ tok/s |