How we got this number
Each generated token reads the whole model from memory once: 39 GB. The Mac mini M5 Pro (24GB) moves 307 GB/s, so the ceiling is 7.9 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 Code Llama 70B
| Mac Studio M5 Ultra (96GB) | 25 tok/s | Check price → |
| Mac Studio M5 Ultra (256GB) | 25 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 13 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 6.3 tok/s | Check price → |
Other models on the Mac mini M5 Pro (24GB)
| gpt-oss 20B | Fast | 60 tok/s |
| Qwen 3 30B (A3B) | Fast | 43 tok/s |
| Qwen3 Coder 30B (A3B) | Fast | 43 tok/s |
| Llama 3.2 Vision 11B | Fast | 32 tok/s |
| Phi 3 14B | Fast | 31 tok/s |
| orca mini 13B | Fast | 31 tok/s |