Meta model product
Muse Glimmer 30B
Muse Glimmer 30B is Meta’s open-weight, dense multimodal model for autonomous agentic work on consumer hardware.
Updated Sep 8, 2026. Default version: Muse Glimmer-30B
LLMBoard Score57.4Muse Glimmer-30B
Coverage20%19 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Muse Glimmer 30B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Muse Glimmer 30B Benchmark Results
Benchmark scores for Muse Glimmer-30B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAA-LCR | Score80.00% | Rank01 | Participants19 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBeam 128K | Score65.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCI Memories Coverage | Score64.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCI Memories Violation Rate | Score26.40% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGAIA2 | Score43.30% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSiren AgentDojo Attack Success Rate | Score28.40% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSiren AgentDojo Utility | Score94.20% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTau3 Banking | Score23.50% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkWildClawBench | Score47.60% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkScreenSpot Pro | Score75.40% | Rank07 | Participants26 | Percentile76.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2026 | Score94.70% | Rank08 | Participants22 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkSkillsBench | Score44.30% | Rank08 | Participants9 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkDeepSearchQA | Score74.60% | Rank10 | Participants10 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score43.60% | Rank11 | Participants24 | Percentile56.52% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score77.00% | Rank13 | Participants39 | Percentile68.42% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score75.50% | Rank14 | Participants34 | Percentile60.61% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score75.80% | Rank14 | Participants18 | Percentile23.53% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score65.90% | Rank18 | Participants24 | Percentile26.09% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score78.80% | Rank28 | Participants55 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score51.70% | Rank32 | Participants35 | Percentile8.82% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score74.00% | Rank36 | Participants69 | Percentile48.53% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score76.00% | Rank36 | Participants113 | Percentile68.75% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score51.20% | Rank49 | Participants55 | Percentile11.11% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score22.00% | Rank65 | Participants103 | Percentile37.25% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,359.56 rating | Rank72 | Participants97 | Percentile26.04% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score83.50% | Rank73 | Participants247 | Percentile70.73% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,427.34 rating | Rank78 | Participants210 | Percentile63.16% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,404.20 rating | Rank101 | Participants121 | Percentile16.67% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,392.10 rating | Rank108 | Participants210 | Percentile48.80% | EvidenceA | Evaluated |
Muse Glimmer 30B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categorymath | Rank49 | Rating / score1,452.81 | Votes207 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank51 | Rating / score1,450.05 | Votes684 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank60 | Rating / score1,479.48 | Votes300 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank67 | Rating / score1,458.40 | Votes247 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank67 | Rating / score1,382.70 | Votes154 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank68 | Rating / score1,352.47 | Votes1,117 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank70 | Rating / score1,482.15 | Votes1,065 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank71 | Rating / score1,422.73 | Votes2,177 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank72 | Rating / score1,359.56 | Votes1,511 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank72 | Rating / score1,359.56 | Votes1,511 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank73 | Rating / score1,468.17 | Votes1,517 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank73 | Rating / score1,437.24 | Votes596 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank73 | Rating / score1,427.73 | Votes373 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank78 | Rating / score1,415.63 | Votes1,279 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank78 | Rating / score1,427.34 | Votes3,693 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank79 | Rating / score1,423.35 | Votes207 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank79 | Rating / score1,419.56 | Votes2,731 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank82 | Rating / score1,445.28 | Votes2,453 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank83 | Rating / score1,449.91 | Votes996 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank85 | Rating / score1,440.19 | Votes628 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank88 | Rating / score1,463.13 | Votes1,065 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank89 | Rating / score1,372.36 | Votes690 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank89 | Rating / score1,427.34 | Votes287 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank92 | Rating / score1,399.30 | Votes684 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank92 | Rating / score1,421.96 | Votes1,692 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank93 | Rating / score1,404.15 | Votes1,279 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank93 | Rating / score1,437.29 | Votes423 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank94 | Rating / score1,369.43 | Votes925 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank94 | Rating / score1,385.67 | Votes914 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank95 | Rating / score1,393.68 | Votes373 | ObservationsN/A | Result date |
Muse Glimmer 30B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.20 input, $0.80 output per 1M via EmpirioLabs AI
- Tracked offerings
- 8
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDmeta/muse-glimmer-30b | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context131.1K | Updated |
| ProviderRequesty | Provider model IDmuse-glimmer-30b | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context131.1K | Updated |
| ProviderEmpirioLabs AI | Provider model IDmuse-glimmer-30b | Regionglobal | Input / 1M$0.20 | Output / 1M$0.80 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDmeta/muse-glimmer-30b | Regionglobal | Input / 1M$0.30 | Output / 1M$1.1 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDmeta/muse-glimmer-30b | Regionglobal | Input / 1M$0.30 | Output / 1M$1.1 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDmeta/muse-glimmer-30b | Regionglobal | Input / 1M$0.35 | Output / 1M$1.5 | Context131.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDmeta/muse-glimmer-30b | Regionglobal | Input / 1M$0.35 | Output / 1M$1.5 | Context131.1K | Updated |
| ProviderFireworks AI | Provider model IDaccounts/fireworks/models/muse-glimmer-30b | Regionglobal | Input / 1M$0.35 | Output / 1M$1.5 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Muse Glimmer 30B Runtime Performance
Provider-specific output speed and catalog latency for Muse Glimmer-30B. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Muse Glimmer 30B Specifications
Technical details for the model's default version.
- Version
- Muse Glimmer-30B
- Released
- Aug 10, 2026
- Knowledge cutoff
- Jan 4, 2026
- Parameters
- 29.6B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Muse Glimmer 30B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMuse Glimmer-30B | Released | LLMBoard57.39 | Parameters29.6B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
Models similar to Muse Glimmer 30B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Muse Spark
Meta
ME
Muse Spark 1.2
Meta
ME
Muse Spark 1.1
Meta
ME
Muse Spark 1.3
Meta
ME
Llama 4 Maverick
Meta
ME
Llama 3.1 405B
Meta
What is Muse Glimmer 30B?
Key information about Muse Glimmer 30B and its available data.
8B-parameter ViT-G/14 perception encoder that accepts interleaved text and images, produces text, and supports a 131,072-token context window. 0.
Data as of 2026-09-08.
FAQ
Common questions about Muse Glimmer 30B.
When was Muse Glimmer 30B released?
Muse Glimmer 30B's default version was released on Aug 10, 2026.
How much does Muse Glimmer 30B cost?
No official standard PAYG price is currently available for Muse Glimmer 30B. The lowest tracked third-party offer starts at $0.20 input and $0.80 output via EmpirioLabs AI.
Who created Muse Glimmer 30B?
Muse Glimmer 30B was created by Meta.
What is the context window for Muse Glimmer 30B?
A context window is not available for the default version.
Is Muse Glimmer 30B open weight?
Yes. The default version is marked as open weight under Apache 2.0.