🏢 MLX Organization

The post describes a multi-turn reinforcement learning run of LFM2.5-8B-A1B, an 8.3B-parameter mixture-of-experts model, using 14 consumer Macs distributed across four countries for rollout generation

Bonsai 27B is a new multimodal flagship model based on Qwen3.6 27B, and it is presented as the first model in its capability class to run on a phone. The release extends Bonsai’s low-bit compression a

The content describes **mlx-community/gemma-4-12B-4bit**, a Hugging Face model converted to **MLX format** from **google/gemma-4-12B** using **mlx-vlm version 0.6.0**. It is a **4-bit quantized**, **m