Meta ships Muse Spark Open: 816B MoE with 1M context, runs on two M5 Ultras
awnihannun · x · 2026-10-16
Meta released the weights of Muse Spark Open, billed as the most capable US open-weight model to date: a natively multimodal 816B-parameter MoE (42B active) with a 1M-token context window, built for coding, agentic long-horizon tasks, and multi-step reasoning. Notably, it's the first model in its class to run on a desktop — two Apple M5 Ultra Mac Studios with the MLX framework, as highlighted by MLX lead Awni Hannun.
Related event: Meta Open-Sources Muse Spark Open, an 816B-Parameter MoE Model(44 posts)→
More from Infra
- Berkeley scholars: concentrated chip supply chain makes a hardwired frontier AI pause feasible — wfithian · 2026-10-16
- Microsoft trained MAI-Base-2 on 16k GB200 GPUs in just 38 days, with 21% MFU — scaling01 · 2026-10-16
- Robotics data tokenization landscape: Khala maps peaq, THOR, BitRobot and Axis — 0xSammy · 2026-10-16
- Signal65 benchmarks: Intel Xeon 6 runs agent workloads 11% faster for less money — ryanshrout · 2026-10-16
- Microsoft's MAI-Base-2: 2.8T-param MoE pretrained on 16k GB200s in just 38 days — scaling01 · 2026-10-16
- Cloudflare and OpenAI pilot: real-time network signals bring unseen pages into ChatGPT search — irvinebroque · 2026-10-16