There’s probably some database or registry. I returned an M4 Mac Mini with 24GB RAM and the base CPU recently and ordered a Mac Studio M4 Max 16/40/16, 128GB RAM.
I also tested on an Macbook Pro M1 Pro, 32GB RAM I have access to, and gave the following prompt:
write a simple Flask API with OpenAPI endpoints
| LLM Model | M1 Pro, 32GB RAM eval rate (tokens/s, 16 graphics cores) | M4 Max, 128GB RAM eval rate (tokens/s, 40 graphics cores) | Intel NUC12i5, 64GB Ram, running Ipex Ollama | M5 32GB RAM eval rate (tokens/s, 10 graphics cores) |
| qwq:32B | 4.97 | 18.6, 16.8, 17.3 | — | 6.0, 6.0, 5.7 |
| qwen2.5:7b | 26.1 | 71.2, 73.2, 72.1 | 5.09, 4.95, 5.27 | 26.1, 25.9, 25.0 |
| a-m-team/AM-Thinking-v1 | 5.73 | 15.6, 15.4 | — | |
| qwen2.5:72b | — | 8.75, 8.84, 8.71 | — |
I vlogged about these, and the setup of my new machine, here.