How we got this number
Each generated token reads the whole model from memory once: 7.4 GB. The Mac Studio M5 Max (40-core GPU, 64GB) moves 614 GB/s, so the ceiling is 83 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 Llama 2 13B
| Mac Studio M5 Ultra (96GB) | 120+ tok/s | Check price → |
| Mac Studio M5 Ultra (256GB) | 120+ tok/s | Check price → |
| Mac mini M5 Pro (24GB) | 33 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 33 tok/s | Check price → |
Other models on the Mac Studio M5 Max (40-core GPU, 64GB)
| Granite 4.2 3B | Fast | 120+ tok/s |
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| minicpm v4.6 1B | Fast | 120+ tok/s |
| Granite 4.1 3B | Fast | 120+ tok/s |
| Llama 3.2 3B | Fast | 120+ tok/s |
| Qwen2.5 3B | Fast | 120+ tok/s |