Baseten launches Muse Spark Open, an open-weight model for coding agents
Original titleMuse Spark Open, an open-weight model for coding agents
AISummary
Baseten says Meta's open-weight Muse Spark Open is available day 0 on its Model APIs and Dedicated Inference. The model has 816B total parameters, 42.7B active during inference, and a 1M token context window with image, video, and audio input.
Baseten says its NVFP4 checkpoint cuts weight size from about 1.6 TB to 540 GB, and a hybrid attention design reduces KV-cache memory 3.7x at 128K context.
AIWhy it matters
The post explains how the model's compressed MoE and hybrid attention cut memory and throughput costs for long coding-agent sessions, a design detail useful for judging deployment economics.
Source: Baseten Blog · baseten.coPublished · added here