Meta picks Apple's MLX as preferred local inference platform; Muse Spark Open runs on two M5 Ultra Mac Studios
awnihannun · x · 2026-10-16
Meta announced Muse Spark Open is optimized to run on two Apple M5 Ultra Mac Studios with the MLX framework, with mlx-lm shipping 0-day support including vision. The MLX team calls this a rare CEO-level Meta-Apple collaboration, positioning mlx-lm as a foundation for quickly supporting new models rather than competing with open-source inference engines. The model is also optimized for SGLang, vLLM, TensorRT-LLM, llama.cpp and more across AMD, Apple, Intel, and NVIDIA silicon, and a new blog details local and distributed LLM inference with MLX and RDMA.
Related event: Meta Open-Sources Muse Spark Open, an 816B-Parameter Model with 1M Context(78 posts)→
More from Infra
- VibeZero: one-shot an entire vibe coding platform on Cloudflare Void — cnakazawa · 2026-10-16
- CoreWeave's debt costs falling: DDTL spreads tightened from S+9.62% to S+2.25% — BenBajarin · 2026-10-16
- SoftBank lines up US IPOs for SB Energy and AI robotics spinoff Roze, valuations top $50B — nordicinst · 2026-10-16
- TRL reproduces Modal's mixed-precision async RL: plain GRPO collapses, SC+MIS holds 0.72 — QGallouedec · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16