Muse Glimmer
Muse Glimmer is Meta’s 30B open-weight multimodal model designed for local, always-on agent workflows. It transfers capabilities from Muse Spark through distillation, followed by longer-context mid-training, supervised tuning, reinforcement learning, and on-policy distillation. The model handles text and images, tool calling, coding, and multi-step plans under configurable reasoning effort. Apache-2.0 weights permit private deployment and adaptation. Consumer hardware viability depends on memory and quantization; local operation does not guarantee reliable autonomous behavior.
2026-08-10
30B
Language model with dedicated perception encoder; further architecture details undisclosed
Apache-2.0
Specifications
- Parameters
- 30B
- Architecture
- Language model with dedicated perception encoder; further architecture details undisclosed
- License
- Apache-2.0
- Type
- multimodal
- Modalities
- textimage
Benchmark Scores
Advanced Specifications
- Model Family
- Muse
- API Access
- Available
- Chat Interface
- Not Available
- Multilingual Support
- Yes
Capabilities & Limitations
- Capabilities
- tool callingcodingreasoningvisionmultilinguallocal inference
- Known Limitations
- Quantization affects memory and qualityAgents require tools and supervision
- Notable Use Cases
- local personal agentsprivate coding assistantsmodel-as-judge evaluation
- Function Calling Support
- Yes
- Tool Use Support
- Yes