cd/entity/mlx-community/Laguna-S-2.1-oQ2e· home› entities› mlx-community/Laguna-S-2.1-oQ2e

grep -l @mlx-community/laguna-s-2.1-oq2e /news/*.json | wc -l → 1

mlx-community/Laguna-S-2.1-oQ2e

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

03:02

2026-07-22

github.com

machine-learning

Running Laguna S 2.1 locally on Apple Silicon: 52 tok/s with 38.5 GB peak memory

The mlx-community/Laguna-S-2.1-oQ2e quantized model running in-process through mlx-vlm on a 128 GB Apple M5 Max achieved a perfect overall score of 1.000 across six tasks, with 40.85 generation tok/s …

// co-occurs with top 7 entities

DWS LLC 1 Apple M5 Max 1 mlx-vlm 1 poolside/Laguna-S-2.1-NVFP4-mlx 1 tanishq-dubey 1 MLX 1 Laguna S 2.1 1

// topics top 4 topics

machine learning 1 large language models 1 ai infrastructure 1 developer tools 1