meta-models/Muse-Glimmer-30B-GGUF
image-text-to-text model by meta-models
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Authors: Meta Superintelligence Lab Model Release Date: August 2026 License: Apache 2.0 Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access. Both text builds are text-only on their own; the two companions are additive. No bf16 GGUF is published — use the base repo if you need full precision. Rough total memory (weights plus a working context): Download a release tagged b10353 or later, or build from source: Drop -DGGMLCUDA=ON for CPU-only. On Apple Metal omit it as well — Metal is on by default. On Debian/Ubuntu you may first need apt-get install -y build-essential cmake curl libcurl4-openssl-dev. Swap in Muse-Glimmer-30B-KQuant-Dynamic-Q4KXL.gguf for the larger build, and…
Read the full model card ↗ · Preview checked 2026-09-24T06:50:31.849Z
Inside the original model card — Document outline
- Muse Glimmer Model Card
- Files
- Get llama.cpp
- Download the weights
- Run
- llama-server
- llama-cli (text)
- llama-mtmd-cli (images)
- Things that will otherwise cost you an hour
- --jinja is not optional
- Never stop on
- -c is split across slots
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
meta-models/Muse-Glimmer-30B-GGUF is a image-text-to-text model repository published by meta-models on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- Not reported
- Recent downloads (30 days)
- 711,072
- Cumulative likes
- 342
- Hugging Face trending score
- 4
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-08-09T17:54:22.000Z
- Last modified
- 2026-08-18T01:04:15.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: meta-models/Muse-Glimmer-30B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-24T06:37:34.998Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.