Laguna Hits 203 TPS on Mac, Launches MLX Inference Optimization Contest

morgymcg · x · 2026-08-07

At 6% the size of DeepSeek V4 Pro, Laguna S 2.1 delivers higher performance and achieves 203 TPS on consumer Macs.

To further accelerate MLX inference, Laguna has teamed up with poolside.ai to launch MLX.fast, a public competition inviting developers to collaborate and optimize the inference engine.

Original post →

More from Infra

Infra channel →