Muse Glimmer 30B
Released early Aug 2026 (exact day not verified). HF org is meta-models, not meta-llama. No first-party Meta API id verified.
- Context window
- 131,072 tokens
- Knowledge cutoff
- 2026-01
- Input
- text, image
- Output
- text
- License
- apache-2.0
- Pricing
- input: $0.3 · output: $1.2 (per 1M tokens (USD) on OpenRouter; open weights free to self-host) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | — | huggingface.co/meta-models/Muse-Glimmer-30B | — |
| OpenRouter | meta/muse-glimmer-30b | openrouter.ai/meta/muse-glimmer-30b | — |
Notable capabilities (3)
- Meta open weights under Apache 2.0: ~29.6B dense text+image model released Apache 2.0 (Llama used a custom community license), with llama.cpp / MLX / ExecuTorch integrations. source
- Local agents on one consumer GPU: Quantized to under 20GB for 24-32GB consumer GPUs/Macs; bundled DFlash drafter for speculative decoding gives ~3.1x speed-up on RTX 5090. source
- Agentic focus for its size: 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. source
Open-weight agentic/vision model for local deployment.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="meta-models/Muse-Glimmer-30B")
Sources: https://huggingface.co/meta-models/Muse-Glimmer-30B , https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model
Other Meta models
Muse Voice Transcribe 1.0 · Muse Spark 1.3 · Omnilingual ASR · Llama 4 Maverick (17B-128E) · Llama 4 Scout (17B-16E)