How we got this number
Each generated token reads the whole model from memory once: 41 GB. The Mac Studio M5 Ultra (256GB) moves 1228.8 GB/s, so the ceiling is 30 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 Qwen 72B
| Mac Studio M5 Ultra (96GB) | 24 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 12 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 6.0 tok/s | Check price → |
| NVIDIA DGX Spark (128GB) | 4.7 tok/s | Check price → |
Other models on the Mac Studio M5 Ultra (256GB)
| 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 20B | Fast | 120+ tok/s |
| gpt-oss 120B | Fast | 120+ tok/s |