Apple MLX
Apple Silicon-native ML framework + model library
Apple Silicon only (M1+)MIT
Apple Silicon-native ML framework + model library
Mistral AI publishes the 123B-parameter weights under Apache 2.0 — Codestral-class reasoning at half the GPU footprint of Llama 3.1 405B. Locally runnable via vLLM, llama.cpp, and MLX.
Editor-curated slugs that route to this platform’s coverage. Reader-voted tags live below.
Be the first to tag this page. A tag becomes publicly visible once it reaches the community vote threshold.
Loading edit history…
MLX is Apple's array framework for ML on Apple Silicon — unified memory model, lazy computation graph, and a growing ecosystem (`mlx-lm`, `mlx-vlm`) for running Mistral / Llama / Phi / Qwen models with first-class M-series performance.
Posts to your status feed
Pick the closest match below, edit the body, and post. Your report carries the #mlx tag automatically so it surfaces here + in the trending-tags rail.
We ran the same 4-bit quant on both backends across coding, summarisation, and long-context recall. MLX wins single-prompt latency; llama.cpp wins throughput. Full numbers + memory traces inside.
All systems normal
No community reports inside the window.
No reports for Apple MLX in the last 2 hours. All clear.