How we got this number
Each generated token reads the active part of the model from memory once: 2.9 GB. The Mac mini M4 (16GB) moves 120 GB/s, so the ceiling is 41 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 Gemma 4 26B (A4B)
Other models on the Mac mini M4 (16GB)
| lfm 2.5 8B (A1B) | Fast | 78 tok/s |
| Llama 2 7B | Fast | 25 tok/s |
| Code Llama 7B | Fast | 25 tok/s |
| DeepSeek Coder 6.7B | Fast | 25 tok/s |
| Llama 2 uncensored 7B | Fast | 25 tok/s |
| orca mini 7B | Fast | 23 tok/s |