- generation:
- 82.4 tokens/s
- quant:
- oQ4e
User reports Mellum2.1-12B-A2.5B-Thinking at 82.4 token/sec on an M1 Max MacBook Pro with 32 GB. Setup is oMLX with an oQ4e quant. The figure is described as achieved in normal thinking and coding work; the post shares a benchmark image and mentions running multiple models on the same machine.