Join us for our inaugural conference, Forge 2026

Model Library/Muse Spark Open 816B-A42B NVFP4

Muse Spark Open 816B-A42B NVFP4

Ready
Deploy on Demand
model path:accounts/fireworks/models/muse-spark-open-nvfp4

Muse Spark Open 816B-A42B NVFP4 checkpoint (meta-models/Muse-Spark-Open-816B-A42B-NVFP4), ModelOpt NVFP4 experts (excl. layers 0/61, attn, lm_head), BF16 MoE, 1M context, multimodal (image/video/audio).

Muse Spark Open 816B-A42B NVFP4 API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Muse Spark Open 816B-A42B NVFP4 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
10/15/2026
Kind
Base model
Provider
N/A
Hugging Face
meta-models/Muse-Spark-1.2-816B-A42B-NVFP4-open

Specification

Calibrated
No
Mixture-of-Experts
Yes
Parameters
816B

Supported Functionality

Fine-tuning
Not supported
Serverless
Not supported
Context Length
1040k tokens
Function Calling
Supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Supported