community pool / model answer

Qwen3.8-27B-MTPLX-Optimized-Speed-FP16

chat · Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16

11.1 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M1 Pro 32GB16-bit11.1 tok/sreported7,00026 GB262,144mlx

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.