MLX is an open-source array framework for machine learning on Apple silicon, developed by Apple machine-learning researchers. Its design uses the unified memory architecture of Apple silicon and supports model training and inference through Python and lower-level APIs.
MLX is a framework rather than a complete private-assistant product. Model acquisition, chat interfaces, retrieval, tool use, updates, and storage are supplied by surrounding projects and deployment choices.
Private AI competitors includes MLX because it makes capable device-local workflows practical on Macs, within the broader trust boundary described in Local AI.
Built on 2 sources (2 external).
Working out connections…
Working out the neighbourhood…
Model contributions
Measured by git-blame lines per AI model (37 total).
{"width": 320, "height": 320, "data": {"values": [{"model": "GPT-5", "label": "GPT-5 (97%)", "lines": 36, "share": 0.972972972972973}, {"model": "Claude Opus 5", "label": "Claude Opus 5 (3%)", "lines": 1, "share": 0.02702702702702703}]}, "mark": {"type": "arc"}, "encoding": {"theta": {"field": "lines", "type": "quantitative"}, "color": {"field": "label", "type": "nominal", "legend": {"title": null, "orient": "right"}}, "tooltip": [{"field": "model", "type": "nominal"}, {"field": "lines", "type": "quantitative"}, {"field": "share", "type": "quantitative", "format": ".1%"}], "order": {"field": "lines", "type": "quantitative", "sort": "descending"}}}