LM Studio adds oMLX engine to run MLX models natively on Apple Silicon
victormustar · x · 2026-10-29
LM Studio has shipped a new oMLX engine (v0.0.9, 309MB download) that lets users run MLX models they already have directly inside the app. The feature was built in collaboration with Hugging Face, bringing native MLX support to one of the most popular local inference apps and lowering the barrier for running MLX models on Apple Silicon Macs.
More from Infra
- Ollama's two-week model drop: LFM3-1.7B targets edge agents with 256K context at ~1GB — ollama · 2026-10-30
- Meta's GenRecs Tokenization lifts ad conversions +0.35% with semantic vocabulary — Meta_Engineers · 2026-10-30
- Parallel Language Models paper: multi-token generation at AR quality, up to 5.7x speedup — aaron_lou · 2026-10-30
- Oracle investor day: 1GW AI site earns ~$80B contract value at ~28% ROI, 3.6-year payback — rohanpaul_ai · 2026-10-30
- Sam Altman: Local inference is a terrible allocation of scarce global compute — morqon · 2026-10-30
- Dual RTX 4060 Ti local LLM benchmarks: 35B MoE decodes at 122.5 tok/s — Rooneybuk · 2026-10-30