Technology / WORLD

Meta releases Muse Spark Open model weights

Meta released weights for Muse Spark Open, a multimodal model it describes as having 816 billion total parameters and about 42 billion active per token.

Reading sizeSources ↓Share story ↗
Conceptual illustration of technology, processors and connected information.Illustration
Symbolic illustration

Meta announced on 15 October that it had released the weights for Muse Spark Open. The company describes it as a multimodal system that handles text, images, audio and video, with 816 billion total parameters, about 42 billion active per token and a context window of up to one million tokens. Meta says the model is designed for coding and long-horizon agent tasks.

The company said the weights can be downloaded through Hugging Face, Amazon SageMaker AI, Google Cloud Model Garden and Microsoft Foundry Models, and that several API providers offer access. Meta also said the model can run with MLX on two Apple M5 Ultra Mac Studio computers and is released under the Muse Model License, which has limited commercial terms. These capability and performance statements come from the company's announcement.

Data

Key figures

Muse Spark Open model scale

Total parameter count stated by Meta.

Total model parameters
816,000,000,000 count
2026-10-15 · Observed
Methodology

Total model parameters stated in Meta's 15 October 2026 Muse Spark Open announcement. The source gives 816 billion; this is represented as 816,000,000,000 using the count unit. It is not an independently verified benchmark.

Updated:

Structured coverage

Subjects and places

Subject proposals

Geographic references

Only source-provided geographic references are shown. Opening an external map is optional. Optional story maps use OpenStreetMap. Opening a map sends your IP address and this site’s address to the map provider; location data remains readable as text without loading the map.

  • United States · Place role: Coverage · Place type: Country or area · Location precision: Regional
    Evidence
    • Explicit preserved editorial country/region; no city or national centroid inferredresearch.meta.ai ↗
Taxonomy version: IPTC Media Topics 2026-Q2

Continue reading