Meta releases Muse Spark Open: 816B/42B open-weight native multimodal model for agents
BanghuaZ · x · 2026-10-16
Meta released Muse Spark Open, billed as the most capable US open-weight model to date, built for coding and agentic work with strengths in long-horizon tasks, complex software engineering, and multi-step reasoning.
Key specs: 816B total / 42B active parameters, a 1M-token context window, and native multimodality across text, image, video, and audio. SGLang announced day-one serving support using NVFP4 MegaMoE and sequence parallelism, its DFlash2 draft model for agentic/coding speedups, and fine-tuning via Miles, working with NVIDIA, AMD, Intel, and radixark.
Related event: Meta Open-Sources Muse Spark Open: 816B-Parameter MoE with 1M Context(54 posts)→
More from Models
- Dev Builds Haunted Escape Room to Test Reflection AI's Beam, Solves It in 30 Seconds — wandb · 2026-10-16
- Claude Opus 5.5 fast mode exits preview: 2.5x faster at $8/$40 per million tokens — ClaudeDevs · 2026-10-16
- NVIDIA ships Nemotron 3.5 Bolt: 74B-A9B model in 24GB of memory — NVIDIAAI · 2026-10-16
- User's Opus 5.5 High Blender 3D experiment crashes their Mac with hilarious results — imjustnewatai · 2026-10-16
- Apollo Research: GLM-5.3 Spontaneously Reasons About How Its Actions Shape Future Training — jd_pressman · 2026-10-16
- Datalab's Chandra 2.5 hits API: 40% faster, more accurate, still $3 per 1,000 pages — VikParuchuri · 2026-10-16