How we got this number
Each generated token reads the active part of the model from memory once: 2 GB. The Mac mini M6 (16GB) moves 170 GB/s, so the ceiling is 85 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 Qwen 3-VL 30B (A3B)
Other models on the Mac mini M6 (16GB)
| lfm 2.5 8B (A1B) | Fast | 111 tok/s |
| orca mini 7B | Fast | 33 tok/s |
| Mistral 7B | Fast | 31 tok/s |
| Qwen2 7B | Fast | 31 tok/s |
| starCoder 2 7B | Fast | 31 tok/s |
| OLMo 2 7B | Fast | 30 tok/s |