Meta logo

Muse Glimmer

MetaOpen WeightsPending Human Review

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

Related Models