Together AI serves Muse Spark Open serverless for agentic coding and multimodal workloads
togethercompute · x · 2026-10-16
Together AI's Serverless Inference now hosts Meta's Muse Spark Open, targeting agentic coding and multimodal workloads. Per its model page, the open-weight model is trained on real developer workflows for higher first-attempt accuracy and reliable tool calling, holds entire projects (thousands of files, legacy code) in a 1M-token context, has native multimodal perception (images, documents, audio, video), built-in intent commentary before acting, and can browse the web, spawn and coordinate subagents, and use computer-use across desktop, mobile, and browser.
Related event: Together AI Launches Meta's Muse Spark Open at Day 0(4 posts)→
More from Infra
- Nvidia's developer base hits 11 million, up ~3.7x from 3 million in 2021 — Beth_Kindig · 2026-10-16
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- vLLM ships Day-0 LoRA RL for Muse Spark Open, lifting AIME from 0.56 to 0.85 — vllm_project · 2026-10-16
- DSpark draft model for Muse Spark Open proposes 7 tokens per pass with 23-42% acceptance — vllm_project · 2026-10-16
- Cloudflare Stream's WebRTC ultra-low-latency live streaming is now Generally Available — ritakozlov · 2026-10-16