Meta releases Muse Spark Open: 816B MoE, 42B active, 1M context, day-0 on Baseten
baseten · x · 2026-10-16
Meta has released the weights for Muse Spark Open, an open-weight omnimodal MoE model it calls the most capable US open-weights model to date, served day 0 on Baseten in NVFP4. Key specs: 816B total / 42.7B active parameters, 1M-token context, and text/image/video/audio input with text output. Co-trained with Muse Code for coding-agent workflows, it uses a compressed MoE block and hybrid global/local attention to cut inter-GPU traffic and KV-cache memory for long agent sessions — enabling screenshot-driven UI debugging, video-to-test-case reproduction, and voice-driven pair programming.
Related event: Meta Open-Sources 816B MoE Model Muse Spark Open; Baseten Offers Day 0 API(2 posts)→
More from coding & agent
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Cortex A/B-tests coding-agent skills and rules by replaying developer corrections before keeping them — Samuele Giampieri · 2026-10-16
- Tool calls are the hidden bottleneck killing AI coding speed — Crabbox and 5 fixes — steipete · 2026-10-16
- Agentic sandbox WorldBox doubles GPT-6 Astra's MazeBench score, 23 to 61 gems — ZhitingHu · 2026-10-16
- Two prompts: Gemini 4 Argon turns a single-player game into full multiplayer — chongdashu · 2026-10-16
- Anthropic and Gray Swan launch $300,000 indirect prompt injection red-teaming contest — bcherny · 2026-10-16