Meta宣布Muse Glimmer

Benchmarks Architecture Text Decoder Perception Encoder Transformers Text-only Inference Prompting the model with images and text Video Inference Multimodal tool calling Object Detection Llama.

Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for local agentic use cases.

Muse Glimmer looks like a really exciting step for practical open-source AI, especially with its focus on local, agentic, and multimodal workloads. A 30B-parameter model combining a 2B vision encoder with a 28B text decoder gives developers a strong foundation for coding, docume…