Meta models
Which Meta models can you run on Modal?
Meta
Muse Spark Open
Meta’s open-weight multimodal model for agentic coding and long-horizon tasks, with 816B total parameters, 42B active per token, and a 1M-token context window.
Multimodal VisionMeta
Muse Glimmer 30B NVFP4
RadixArk's NVFP4/MXFP8 quantization of Meta's Muse Glimmer 30B agentic model: text-only, 128K context, controllable reasoning, and tool calling.
TextMeta
Muse Glimmer 30B BF16
Meta's open agentic model for local hardware: a dense 30B model distilled from Muse Spark, with 128K context, controllable reasoning, and Apache 2.0 weights.
Text
| Model | Architecture | Context | Modalities | Input / Output |
|---|---|---|---|---|
| Muse Spark Open | 816B MoE · 42B active | 1M | Text · Image · Audio | $1.25 / $4.25 |
| Muse Glimmer 30B NVFP4 | 30B dense | 128K | Text | Dedicated only |
| Muse Glimmer 30B BF16 | 30B dense | 128K | Text | Dedicated only |
All prices per million tokens. Dedicated Endpoint compute is billed by the second. See compute pricing.
Latest updates

Scaling Intelligence: A landmark commission and exhibition

Sandbox resourcing: burst, don't reserve
Why you're paying for capacity you aren't using, and how to pay only for what you use.

Modal becomes a gVisor maintainer
Modal runs upwards of 40 million gVisor containers every day. Here's why we bet on it, what we've built into it, and where we want to take it next.
