meta
Meta: Muse Glimmer 30B (batch)
meta/muse-glimmer-30b:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Meta's Muse Glimmer 30B is a dense, open-weight multimodal model released under Apache 2.0, distilled from Muse Spark and built for autonomous agentic workloads on consumer hardware. It accepts text and image input, produces text, and supports a roughly 131K-token context, tool calling, structured outputs, and selectable reasoning effort. The OpenRouter catalog lists this entry as a batch variant with reasoning always enabled. Vendor-reported evaluations suggest strong results for its size class, but independent verification is limited.[1][2]
Strengths
- Engineered for local deployment: the model card says quantized 4-bit weights fit consumer GPUs and a companion drafter model speeds up generation with minimal reported quality loss.[2]
- Vendor-reported benchmarks indicate strong agentic capability for its size, including multi-step reasoning, schema-precise tool use, and failure recovery.[2]
- Broad feature surface in the catalog: text and image input, tool calling, structured outputs, adjustable reasoning effort, and training across more than 100 languages.[1][2]
Limitations
- The vendor cautions it can produce inaccurate or biased responses, may err in multi-step reasoning on novel scenarios, handles video only as individual frames, and has not been evaluated on every language in its training data.[2]
- Adversarial evaluations reported by the vendor show residual prompt-injection and information-flow risks; it recommends deploying behind external guardrails, and audio input or output is unsupported.[2]
- Evidence is largely a single vendor model card plus a catalog entry; benchmark figures are vendor-reported rather than independently verified, so validate performance and cost on your own workload before adopting.[1][2]
Where to use it
- Local, on-device agents that plan long-horizon tasks and invoke tools may fit its design, though real-world reliability should be tested first.[2]
- Coding assistants and software-engineering agent workflows are plausible given the vendor's reported results, pending validation on your repositories.[2]
- Pipelines that interpret screenshots, charts, or documents alongside text could use its multimodal input where supported latency permits.[2]
Sources
- [1] OpenRouter catalog · Meta: Muse Glimmer 30B (batch)Sources checked: Nov 13, 2026
- [2] Model documentation · Meta: Muse Glimmer 30B (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- meta/muse-glimmer-30b:batch
- Canonical ID
- meta/muse-glimmer-30b-20260810
- Creator
- meta
- Added to OpenRouter
- 09.08.2026
- Context length
- 131,072
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.240 / out $0.960
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: mandatory · default medium · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | BB — next 30% of the cohort | — |
| Agents | BB — next 30% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 6.3 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 49 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 8.5 | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 26% · rank 100 | 1,070Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 35.7% · rank 81 | 1,160Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 29.9% · rank 94 | 1,109Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 39.6% · rank 63 | 1,198Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 39.1% · rank 73 | 1,186Elo | BB — next 30% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrabf16 | 131,072 | $0.240 | $0.960 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.