Model Detail Human reviewed

Muse Glimmer 30B

Meta Muse Glimmer 30B is an Apache 2.0 open-weight, dense multimodal agentic model designed for always-on local workflows. It combines text and image understanding, long-context reasoning, coding, tool calling, and computer-use capabilities. Meta publishes BF16 weights, official GGUF quantizations targeting 24GB and 32GB VRAM, and ExecuTorch packages for Metal and CUDA.

MetaMUSE GLIMMERapache-2.02026-08-10

Deployment and license note

Muse Glimmer understands images but does not generate images. Meta targets 24GB VRAM with the official 17GB K-Quant build, 32GB VRAM with the higher-quality dynamic K-Quant build, and 64GB VRAM for full precision. Long contexts and vision inputs add runtime memory, so leave extra headroom. DFlash acceleration is optional and depends on runtime support.

Parameters
30B
Dense model
Context window
131K
Long context
Architecture
muse glimmer multimodal transformer
dense
Quality score
96
Planner signal

Task Fit

Code AgentSupported

Tool use, repo work, terminal workflows, and coding benchmarks.

CodeSupported

Code generation, debugging, refactoring, and benchmark signal.

ChatSupported

General writing, Q&A, and assistant use.

RAGSupported

Document QA benefits from long context and instruction following.

VisionSupported

Image or visual understanding, not necessarily image generation.

Image GenerationNot a fit

Not marked for image generation in the current library.

Video GenerationNot a fit

Not marked for video generation in the current library.

VoiceNot a fit

Not marked for voice in the current library.

Source Confidence

Overallhigh · 100/100
ParametersReviewed / seeded
Task fitReviewed / seeded
MemorySeeded artifact
LicenseSource / seed
BenchmarksAvailable
Hardware fitCalculated

Variants and Quant Artifacts

Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.

3 artifacts
QuantFormatQualityMin RAMReco RAMRuntimeAction
Q4_K_Mggufbalanced24GB32GBllama.cpp, lm-studio, mlx, executorch Plan with this
Q4_K_XLggufbalanced32GB40GBllama.cpp, lm-studio, mlx, executorch Plan with this
BF16safetensorshigh64GB80GBtransformers, vllm, sglang, executorch Plan with this

Benchmarks

GPQA Diamond83.5%
Ifbench77%
SWE Bench Verified76%
Mcp Atlas75.5%
MMMU Pro74%
Osworld Verified65.9%
Terminal Bench 2.151.7%
SWE Bench Pro51.2%

Source and Review

Hugging Facemeta-models/Muse-Glimmer-30B
OllamaNot mapped
VerificationHuman reviewed
Artifact sourceofficial-muse-glimmer-q4_k_m-weights
Default variantMuse Glimmer 30B Multimodal
Tool callingSupported

Execution evidence

Run Muse Glimmer 30B with a documented recipe

Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.

Browse all recipes →

No verified recipe is linked to this record yet.

Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.

Similar Models

Continue planning your local AI setup