Muse Glimmer 30B
Meta's 30B open-weight dense multimodal model for local, long-running agentic workflows, distilled from the larger Muse Spark teacher and sized to run on a single consumer GPU.
Routable on MicroRouter
Use meta/muse-glimmer-30b via the API →- Price
- Not published
- Meta positions it for local use with no per-token cost; hosted routes price independently
- Weights
- Released
- Apache 2.0 on Hugging Face, in BF16, GGUF, and ExecuTorch builds
- Parameters
- 30B dense
- ~29.6B per the model card, distilled from the Muse Spark teacher
- Context
- 128K
- Model card lists 131,072+ tokens combined input and output
Publisher pricing
Pricing below comes from the release announcement and does not represent a MicroRouter route or price.
Not published
The publisher announcement does not list an API price. MicroRouter does not estimate one.
Publisher-reported benchmarks
Results are grouped by unit. Percentage, Elo, and task-count results never share a scale.
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| SWE-Bench Verified | 76.0 | Meta | Aug 10, 2026 | Announcement ↗ |
| SWE-Bench Pro | 51.2 | Meta | Aug 10, 2026 | Announcement ↗ |
| TerminalBench 2.1 | 51.7 | Meta | Aug 10, 2026 | Announcement ↗ |
| OSWorld-Verified | 65.9 | Meta | Aug 10, 2026 | Announcement ↗ |
| GPQA Diamond | 83.5 | Meta | Aug 10, 2026 | Announcement ↗ |
- — Meta's comparison baselines are Gemma4-31B and Qwen3.6-27B.
- — Meta notes ~4-bit quantization may reduce performance versus full precision.
- — Meta reports the benchmark figures; MicroRouter has not reproduced them.
Independent measurements
Artificial Analysis runs its own evaluations and timing against each model's first-party API. These are the only numbers on this page not reported by the publisher.
Muse Glimmer (high) ranks #88 of 448 model families on their Intelligence Index.
- Intelligence Index
- 35.1
- Composite of their evaluations
- Coding Index
- 49.0
- Coding evaluations only
- Blended price
- $0.58
- USD per 1M tokens, 3:1 input to output, first-party list
- Output speed
- 103
- Median tokens per second
- First answer token
- 20s
- Median seconds, including reasoning
Muse Glimmer (high) on Artificial Analysis ↗
Source: Artificial Analysis ↗, read Sep 2, 2026. Measured on the model's first-party API, not a MicroRouter route.
What is not independently confirmed
- Every figure on this page is self-reported by the cited publisher. MicroRouter did not run these benchmarks.
- Benchmark harnesses are not standardised. Results sharing a name across vendors have not been confirmed to use identical runs.
- Publisher pricing can change, and introductory phases have stated end dates.
- Muse Glimmer 30B is routable through MicroRouter today; live pricing on its model page is authoritative over the publisher figures here.
Related coverage
Other release dossiers and the current MicroRouter catalog.
Sources
- Read at Meta ↗
Meta AI Research announcement
Published Aug 10, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 2, 2026
Editorial reference revised 2026-09-02. Catalog status comes from the generated routing snapshot.