Muse Spark Open — 816B Demo

Built with Muse Spark Open. Meta's 816B-total / 42B-active multimodal Mixture-of-Experts model, served here in its NVFP4 form via Hugging Face Inference Providers (Together).

816B total params 42B active / token 1M context NVFP4 · Together Text + image in Text out

1 · Connect your Hugging Face account

This Space hosts no weights — the NVFP4 model needs ~700 GB of VRAM, so it can't run on a Space GPU. Instead this page calls it through Inference Providers, and inference is billed to your Hugging Face account.

You'll need: (a) approved access to the gated model, and (b) a Hugging Face token with Inference Providers credits / a PRO plan.

Get a token at huggingface.co/settings/tokens · Request model access at meta-models/Muse-Spark-Open-816B-A42B-NVFP4 · Credits / billing at huggingface.co/settings/billing

Recommended sampling for this model: temperature 1.0, top_p 1.0 — those are used for every call.

2 · Chat

Hi — ask me anything, or attach an image and ask about it. Try an example below to start.

How this demo works