How we got this number
Each generated token reads the active part of the model from memory once: 2.1 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 Qwen3.5 35B (A3B)
Other models on the Mac mini M5 Pro (24GB)
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| gpt-oss 20B | Fast | 60 tok/s |
| Llama 3.1 8B | Fast | 50 tok/s |
| Qwen 7B | Fast | 50 tok/s |
| dolPhin 3 8B | Fast | 50 tok/s |
| Gemma 7B | Fast | 49 tok/s |