How we got this number
Each generated token reads the whole model from memory once: 7.4 GB. The Mac mini M4 (16GB) moves 120 GB/s, so the ceiling is 16 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
Other models on the Mac mini M4 (16GB)
| lfm 2.5 8B (A1B) | Fast | 78 tok/s |
| minicpm v4.6 1B | Fast | 60 tok/s |
| Gemma 2 2B | Fast | 60 tok/s |
| codeGemma 2B | Fast | 60 tok/s |
| Gemma 2B | Fast | 57 tok/s |
| smollm 2 1.7B | Fast | 53 tok/s |