@Youssofal_: 72+ TPS on Qwen 3.6 27B on a Macbook pro M5 max. MTPLX V2 out now! The fastest way to run models on MLX.

X AI KOLs Following Tools

Summary

MTPLX V2 is released, claiming 72+ tokens per second on Qwen 3.6 27B running on a Macbook Pro M5 Max via MLX.

72+ TPS on Qwen 3.6 27B on a Macbook pro M5 max. MTPLX V2 out now! The fastest way to run models on MLX. https://t.co/ppfmzsED6v
Original Article
View Cached Full Text

Cached at: 07/08/26, 04:26 AM

72+ TPS on Qwen 3.6 27B on a Macbook pro M5 max.

MTPLX V2 out now!

The fastest way to run models on MLX. https://t.co/ppfmzsED6v

Similar Articles

@nash_su: Mac inference speed doubled. MTPLX is an integrated solution combining MLX and MTP, specifically optimized for model inference on Apple Silicon. By using models with a custom MTP head, it can deliver doubled inference speed. I tested it with Qwen3.6-27…

X AI KOLs Timeline

MTPLX is an integrated solution combining MLX and MTP, specifically optimized for model inference speed on Apple Silicon. Tests show that Qwen3.6-27B achieves double the inference speed of LM Studio, and it also integrates fan management.