Muse Glimmer 30B
Unavailable in this round
Language modelOpen source
Muse Glimmer 30B
Meta
- Released
- August 10, 2026
- Data date
- September 8, 2026
- Speed
- 105.6 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
- Input
- Text, Image
- Output
- Text
Muse Glimmer 30B is Meta’s open agent model for local use. Unlike Muse Spark, the focus is a downloadable checkpoint that combines image understanding and controllable reasoning in a compact architecture.
The weights are released under Apache 2.0. Meta positions Glimmer for a single consumer GPU, quantized variants, and local runtimes such as llama.cpp, MLX, and ExecuTorch.
Specifications and access
| Specification | Value and source |
|---|---|
| Weights | Open weightsSource |
| Access | API, LocalSource |
| Parameters | 29.6BSource |
| Context window | 131,072 tokensSource |
| Knowledge cutoff | January 4, 2026Source |
| Notes | Apache-2.0 model with 29.6B parameters and a 128K context window.Source |
| License | Apache-2.0Source |
| Release | 2026-08Source |
| Parameters | 29.6 BSource |
| Active parameters | 29.6 BSource |
| Architecture | dense causal transformer with approximately 1.8B ViT perception moduleSource |
| Input | Text, ImageSource |
| Output | TextSource |
| Languages | >100Source |
Page 1 of 3
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MCP Atlas (Show measurement, test conditions, and source)
- Source value
- 75.5
- Score
- 75.5
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
DeepSearch QA (Show measurement, test conditions, and source)
- Source value
- 74.6
- Score
- 74.6
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
tau3 Banking (Show measurement, test conditions, and source)
- Source value
- 23.5
- Score
- 23.5
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
WildClaw (Show measurement, test conditions, and source)
- Source value
- 47.6
- Score
- 47.6
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
Gaia2 (Show measurement, test conditions, and source)
- Source value
- 43.3
- Score
- 43.3
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
SkillsBench (Show measurement, test conditions, and source)
- Source value
- 44.3
- Score
- 44.3
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
OSWorld Verified (Show measurement, test conditions, and source)
- Source value
- 65.9
- Score
- 65.9
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
SWE-Bench Pro (Show measurement, test conditions, and source)
- Source value
- 51.2
- Score
- 51.2
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
SWE Verified (Show measurement, test conditions, and source)
- Source value
- 76
- Score
- 76
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
TerminalBench 2.1 (Show measurement, test conditions, and source)
- Source value
- 51.7
- Score
- 51.7
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
SciCode (Show measurement, test conditions, and source)
- Source value
- 43.6
- Score
- 43.6
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
Charxiv (Show measurement, test conditions, and source)
- Source value
- 78.8
- Score
- 78.8
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Meta Muse Glimmer model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Muse benchmark table; configuration as reported by card
Page 1 of 3
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Earlier tests
Pelican on a bicycle
A community classic for free-form SVG drawing.
Muse Glimmer 30B
Reasoning (requested): high
Current attempt
- Run date
- Oct 5, 2026
- API provider
- openrouter
- Requested API model
- meta/muse-glimmer-30b
- API model reported in response
- meta/muse-glimmer-30b
- Reasoning setting
- high
- Pinned endpoint
- Phala | meta/muse-glimmer-30b-20260810
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 94 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (2)
- Oct 2, 2026API request failedReasoning setting: high
- Oct 1, 2026API request failedReasoning setting: high
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Popularity
45.4 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Speed | Median across serving providers, High effort. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. |
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Input | Documented modalities. Retrieved September 8, 2026. |
| Output | Documented modalities. Retrieved September 8, 2026. |
| Research status | Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | max-output-tokens Original wording No model-specific maximum output in the checked card. |
| Not found in the inspected sources | api-model-id Original wording The checked card does not publish a stable API model identifier. |
| Additional source | Model metadata · Meta AI Research, Introducing Muse Glimmer · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |