How we got this number
Each generated token reads the whole model from memory once: 19 GB. The Mac mini M6 (32GB) moves 170 GB/s, so the ceiling is 8.9 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 34B
| Mac Studio M5 Ultra (96GB) | 52 tok/s | Check price → |
| Mac Studio M5 Ultra (256GB) | 52 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 26 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 13 tok/s | Check price → |
Other models on the Mac mini M6 (32GB)
| lfm 2.5 8B (A1B) | Fast | 111 tok/s |
| Qwen 3 30B (A3B) | Fast | 40 tok/s |
| Qwen3 Coder 30B (A3B) | Fast | 40 tok/s |
| Llama 2 7B | Fast | 36 tok/s |
| Code Llama 7B | Fast | 36 tok/s |
| DeepSeek Coder 6.7B | Fast | 36 tok/s |