Today we’re releasing Muse Spark Open, the most capable US open-...

Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning.
Key Model Specs:
→ 816B total / 42B active parameters
→ 1M token context window
→ Natively multimodal across text, image, video, audio
It also runs on leading inference engines like SGLang, vLLM, TensorRT-LLM, Hugging Face Transformers, llama.cpp, and Unsloth with optimizations for AMD, Apple, Intel, and NVIDIA silicon.
Developers can further customize the model with PyTorch, including TorchTitan for fine-tuning.
Download the weights on Amazon SageMaker AI, Google Cloud Model Garden, Hugging Face, and Microsoft Foundry Models.
Weights are released under the Muse Model License, with limited commercial terms that let many developers use the model for free.
Learn more on our research blog: go.meta.me/musesparkopen
Download the weights: huggingface.co/collections/me…

