Muse Spark Open

Muse Spark Open is the open-weight release of Muse Spark, Meta's agentic and coding model. Run it two ways:

  • Self-host: download a checkpoint and serve it on your own GPUs with SGLang, vLLM, or another runtime, so every prompt and response stays inside your infrastructure.
  • Hosted provider: call it through a hosted provider's API, with no GPUs to provision.

Model variants

ModelParametersArchitectureContext window
Muse Spark Open816B total, 42B activeSparse mixture of experts, multimodal (text, image, audio, and video input; text output)1,048,576 tokens

Architecture

Muse Spark Open is a sparse mixture-of-experts transformer with built-in perception encoders. Each token routes to a small subset of experts, so per-token compute tracks the 42B active parameters. Serving still loads the full 816B weights into VRAM, which sets the hardware footprint.

Supported languages

Muse Spark Open was trained on data from more than 100 languages.

Checkpoints and hardware

Muse Spark Open ships in two checkpoint formats:

  • BF16: the full-precision reference, about 1.65 TB of weights. Serves on eight GPUs, such as 8 × B300.
  • NVFP4: stores most weights in 4-bit and keeps some layers in BF16, about 537 GB of weights. Serves on a single 4-GPU NVIDIA Blackwell node.

Serving needs memory beyond the weights for the key-value cache, activations, and runtime overhead: budget roughly 2 TB of VRAM for BF16. Get the model has the download, and Hardware platforms covers the NVIDIA, AMD, and Intel configurations, with sample commands.

License

Muse Spark Open is released under the Muse Model License(opens in new tab). Use is also subject to the Acceptable Use Policy(opens in new tab).

Launch partners

The Muse Spark Open launch ecosystem includes:

  • Model catalogs: Amazon SageMaker AI, Google Cloud Model Garden, and Microsoft Foundry Model Catalog
  • Inference platforms: Baseten, Fireworks AI, Groq, Modal, Nebius, and Together AI
  • Tooling: Hugging Face, llama.cpp, MLX, NVIDIA TensorRT-LLM, SGLang and RadixArk, Unsloth, and vLLM and Inferact
  • Silicon: AMD, Apple, Intel, and NVIDIA
  • Gateway: OpenRouter

Get started

Get the modelDownload the weights from Hugging Face and verify your setup.
Prompting guideExamples for chat, system prompts, reasoning, tool calling, and image, video, and audio input.
Run inferenceSelf-host with SGLang, vLLM, or another runtime, or call a hosted provider.

Next steps

Now that you know what the open-weight release offers, pick a checkpoint and download the weights. When you're ready to serve, choose a runtime, then tune throughput and output quality with the recommended settings.