{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/muse-glimmer-30b/","md":"https://postcutoff.com/m/muse-glimmer-30b/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"muse-glimmer-30b","name":"Muse Glimmer 30B","org":"Meta","family":"Muse","released":"2026-08","status":"current","type":"llm","modality_in":["text","image"],"modality_out":["text"],"open_weights":true,"model_license":"apache-2.0","context_window":131072,"max_output":null,"knowledge_cutoff":"2026-01","pricing":{"input":0.3,"output":1.2,"unit":"per 1M tokens (USD) on OpenRouter; open weights free to self-host","source":"https://openrouter.ai/meta/muse-glimmer-30b"},"price_line":"$0.30 in, $1.20 out per 1M tokens","access":[{"provider":"Hugging Face","url":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"provider":"OpenRouter","model_id":"meta/muse-glimmer-30b","url":"https://openrouter.ai/meta/muse-glimmer-30b"}],"capabilities":[{"name":"Meta open weights under Apache 2.0","detail":"~29.6B dense text+image model released Apache 2.0 (Llama used a custom community license), with llama.cpp / MLX / ExecuTorch integrations.","first":false,"discovered":"launch","source":"https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model"},{"name":"Local agents on one consumer GPU","detail":"Quantized to under 20GB for 24-32GB consumer GPUs/Macs; bundled DFlash drafter for speculative decoding gives ~3.1x speed-up on RTX 5090.","first":false,"discovered":"launch","source":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"name":"Agentic focus for its size","detail":"Optimized for multi-step reasoning, reliable tool use and failure recovery; Meta benchmarks it as competitive with Gemma4-31B and Qwen3.6-27B on agentic/coding evals.","first":false,"discovered":"launch","source":"https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model"}],"entry":null,"notes":"Released early Aug 2026 (exact day not verified). HF org is meta-models, not meta-llama. No first-party Meta API id verified.","verified":"2026-09-29","body_md":"Open-weight agentic/vision model for local deployment.\n\n```python\nfrom transformers import pipeline\npipe = pipeline(\"image-text-to-text\", model=\"meta-models/Muse-Glimmer-30B\")\n```\n\nSources: https://huggingface.co/meta-models/Muse-Glimmer-30B , https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model","page_url":"https://postcutoff.com/m/muse-glimmer-30b/","events_after":1945,"major_after":444,"historic_after":85,"missing_at_launch":241,"events_since_release":null,"you_url":"https://postcutoff.com/you/muse-glimmer-30b/","briefings":{"xs":"https://postcutoff.com/briefings/cutoff-2026-01-xs.md","s":"https://postcutoff.com/briefings/cutoff-2026-01-s.md","m":"https://postcutoff.com/briefings/cutoff-2026-01-m.md","full":"https://postcutoff.com/briefings/cutoff-2026-01.md"}}