Meta releases Muse Spark Open: 816B-param open-weight model with 1M context, natively multimodal
IanAndrewsDC · x · 2026-10-16
- Meta officially released Muse Spark Open, billed as the most capable US open-weight model to date, built for coding and agentic work: long-horizon tasks, complex software engineering, and multi-step reasoning.
- Key specs: 816B total / 42B active parameters, 1M token context window, natively multimodal across text, image, video, and audio.
- It's live on the Dell Enterprise Hub on Hugging Face with an NVFP4 variant deployable via SGLang v0.5.21, alongside NVIDIA Nemotron 3.5 Super VL (120B total / 12B active, 1M context, native MTP speculative decoding, deploy with vLLM v0.31.0).
Related event: Meta Open-Sources Muse Spark Open, Its Strongest US Open-Weights Model(62 posts)→
More from Infra
- Google's Willow chip cuts quantum errors 40x, raising Q-Day concerns for Bitcoin — jamestagg · 2026-10-16
- Vibe Coding a Data Pipeline Is Easy; Running It at Billions of Rows Is Not — Zachly · 2026-10-16
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16