Muse Glimmer 30B
5242°
Run this model
Offers / Ads
Meta | 131,072 token context | $0.30/M input, $1.20/M output. Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.
Guides for this model
Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Muse Glimmer 30B is an open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and built specifically for autonomous agents running on consumer hardware. At roughly 30 billion parameters it accepts interleaved text and images, covers more than 100 languages, and carries an Apache 2.0 licence. If you want a capable local agent that handles tool use, code and image understanding without a cloud dependency, this is the size class to look at.
Known for
- Purpose-built for agentic workflows: tool use, failure recovery and multi-step planning.
- Runs locally on consumer hardware under Apache 2.0, no cloud required.
- Dedicated ViT-G perception encoder handles screenshots, charts and documents.
- Controllable reasoning effort lets you trade quality for speed per request.
- Compatible with OpenClaw, Hermes Agent and other agentic scaffolds out of the box.
Watch out for
- Output-only text: the model reads images but cannot generate them.
- Knowledge cuts off January 4, 2026; anything after that it does not know.
- A 30B dense model needs meaningful VRAM; check your hardware before downloading.
Prompts to try
Multi-step debugging agent
You have a Python script that scrapes a webpage, parses a JSON response, and writes results to a CSV. The script fails silently and produces an empty file. Walk through each stage methodically, identify where the failure is most likely occurring, write a corrected version of the script, and explain what you changed and why.
Screenshot to action plan
I'm attaching a screenshot of a web application's dashboard. Identify every interactive element visible, describe what each one does based on its label or icon, then write a step-by-step plan an agent could follow to export the data shown in the main table to a local CSV file.
Tool-call failure recovery
You called a weather API with the correct parameters and received a 429 rate-limit error. You need the current temperature in three cities for a report due in two minutes. Reason through your options, decide on a fallback strategy, and write the revised tool-call logic including retry handling and a graceful degradation path if all retries fail.
Compare with
- Muse Spark 1.3 ContributorAPI-only model1,048,576 token context · $0.10/M input, $0.20/M output
- Muse Spark 1.3API-only model1,048,576 token context · $1.25/M input, $4.25/M output
- Muse WonderAPI-only model1,048,576 token context · $4.00/M input, $20.00/M output
- Muse Spark 1.2API-only model1,048,576 token context · $1.25/M input, $4.25/M output
More text models from meta
Questions people ask
- Can I run Muse Glimmer 30B locally?
- Yes. The weights are open under Apache 2.0 and the model is available on Hugging Face at meta-models/Muse-Glimmer-30B. Meta explicitly optimised it for consumer hardware, though a dense 30B model will demand meaningful VRAM.
- What does it cost to use via API, and how long is the context?
- Pricing is $0.30 per million input tokens and $1.20 per million output tokens, with a context window of 131,072 tokens.
- How is Glimmer different from Muse Spark?
- Muse Glimmer 30B is distilled from Muse Spark and trades some of Spark's raw scale for a size that runs on consumer hardware, with the distillation process specifically targeting agentic capabilities rather than general-purpose performance.
Captain's verdictA rare thing: an open, locally runnable agent model that treats tool use and failure recovery as first-class features rather than afterthoughts.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Muse Glimmer 30B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153