Muse Glimmer
Meta's open-weight 30B-parameter agentic model, distilled from Muse Spark, that runs locally on consumer hardware with tool use and multimodal input.
Overview
Meta released Muse Glimmer on Hugging Face on August 10, 2026 (huggingface.co/blog/muse-glimmer), an open-weight 30-billion-parameter causal language model (a 2B vision encoder plus a 28B text decoder) distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware, under an Apache 2.0 license. It combines multi-step reasoning, tool use, multimodal understanding (via a dedicated perception encoder for interleaved text and images), and failure recovery in a single model that runs locally without cloud infrastructure, using a hybrid sliding-window/full-attention architecture, grouped-query attention, and DFlash speculative decoding for faster generation. Meta reported scores of 75.5 on MCP-Atlas, 74.6 on DeepSearch QA, and 51.2 on SWE-Bench Pro, and shipped day-0 support across Transformers, llama.cpp (including GGUF quantized builds), vLLM, and Inference Endpoints, plus training data spanning more than 100 languages.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- 30B parameters (2B vision encoder + 28B text decoder), Apache 2.0 open-weight license
- Distilled from Muse Spark for local, autonomous agentic use on consumer hardware
- Multimodal input via dedicated perception encoder (interleaved text and images)
- Hybrid sliding-window/full attention with grouped-query attention for efficient KV-cache use
- DFlash speculative decoding for faster local generation
- Day-0 support in Transformers, llama.cpp/GGUF, vLLM, and Inference Endpoints
- 75.5 on MCP-Atlas, 74.6 on DeepSearch QA, 51.2 on SWE-Bench Pro; trained on 100+ languages
Use cases
- Running agentic assistants locally without network access
- On-device tool-calling agents for coding and multi-step tasks
- Multimodal agents that interpret screenshots, charts, and documents
Pricing
Free and open-weight (Apache 2.0); self-hosted, no API fee from Meta.
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 10 Aug 2026
- Record updated
- 23 Sept 2026
- Record last checked
- 23 Sept 2026