How we got this number
Each generated token reads the whole model from memory once: 1.1 GB. The Mac mini M5 Pro (24GB) moves 307 GB/s, so the ceiling is 120+ 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 DeepSeek-R1 1.5B
| Mac mini M6 (16GB) | 120+ tok/s | Check price → |
| Mac mini M6 (32GB) | 120+ tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 120+ tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 120+ tok/s | Check price → |
Other models on the Mac mini M5 Pro (24GB)
| minicpm v4.6 1B | Fast | 120+ tok/s |
| Llama 3.2 1B | Fast | 120+ tok/s |
| Qwen2.5 3B | Fast | 120+ tok/s |
| Qwen 3 1.7B | Fast | 120+ tok/s |
| Gemma 2 2B | Fast | 120+ tok/s |
| Qwen2.5 Coder 3B | Fast | 120+ tok/s |