How we got this number
Each generated token reads the whole model from memory once: 49 GB. The Mac mini M4 (16GB) moves 120 GB/s, so the ceiling is 2.4 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 Qwen2.5-VL 72B
Other models on the Mac mini M4 (16GB)
| starCoder 2 15B | Usable, but slow | 5.8 tok/s |