Muse Spark Open
Meta's Muse Spark Open, an 816B-parameter mixture-of-experts coding model with a 1 million-token context window, is now available in Amazon SageMaker JumpStart in BF16 and NVFP4 variants.
The Deploy Log | Models | Free, no signup
8 rows in The Deploy Log from 7 companies name Muse Spark Open: Amazon Web Services, OpenRouter, Together AI, Hugging Face, Baseten, llama.cpp and Vercel. They are listed from to , each by its publisher's date or, where the record carries none, its edition's date. Newest first, each linking the publisher's own page.
| Company | First row dated | Days after the first |
|---|---|---|
| Amazon Web Services | First | |
| Baseten | First | |
| Hugging Face | First | |
| llama.cpp | First | |
| OpenRouter | First | |
| Together AI | First | |
| Vercel | First |
Meta's Muse Spark Open, an 816B-parameter mixture-of-experts coding model with a 1 million-token context window, is now available in Amazon SageMaker JumpStart in BF16 and NVFP4 variants.
Meta Muse Spark Open is available on OpenRouter at $1.25 per 1M input tokens and $4.25 per 1M output tokens.
Meta Muse Spark Open is now live on Together AI.
Meta's open-weight multimodal mixture-of-experts model with ~816B total parameters, ~42B active per token, and up to 1M context is available on Hugging Face.
Meta Muse Spark Open and NVIDIA Nemotron 3.5 Super VL are available through Baseten Model APIs.
llama.cpp b11671 adds Muse Spark Open model support for text, vision, and audio.
Meta's Muse Spark Open is available on AI Gateway with 1M-token context and no training.
Muse Spark Open model is now available on Amazon SageMaker JumpStart.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.