Skip to main content
AI Choice Engine

Meta

Muse Glimmer 30B

Muse Glimmer 30B is a Meta model with 131K context, Not verified in / Not verified out per million tokens, last verified October 2, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

Muse Glimmer 30B is Meta's open-weight smaller Muse model for efficient self-hosting.

Recorded profile verification October 2, 2026Individual provider fields may change

AI model specification details
SpecificationMuse Glimmer 30B
ProviderMeta
TierBalanced
Context window131K
Max outputNot verifiedUnverified
Input / 1M tokensNot verifiedUnverified
Output / 1M tokensNot verifiedUnverified
WeightsOpen
Parameters~29.6B total including vision (dense; marketed as 30B)
Reasoning levelslow, medium, high, xhigh
Modalitiestext, image
LicenseApache 2.0
ReleasedAugust 10, 2026

Pricing tiers: Apache 2.0 weights, not served by Meta Model API; no first-party token tariff is verified. Self-hosting incurs compute/storage costs. Native config context is 131,072; longer-context support is a publisher claim, not an independently verified maximum.

Best for

  • Open-weight deployments
  • Single-GPU serving
  • Cost-sensitive

Watch out

Template reasoning_strength supports low/medium/high/xhigh, default high. BF16 download is about 60GB; published 17GB/20GB GGUFs need a separate 1.4GB vision projector and optional 1.6GB draft. Meta targets 24GB/32GB hardware by build; actual fit and speed depend on runtime/context. Native Transformers support requires 5.15+. A separate hard output cap remains unknown.

History

Muse Glimmer 30B timeline

Release and status events for this model that passed two-source verification — dated, sourced, and linked.

Source receipts

Catalog figures for this model were checked against the following sources.

Common questions

Muse Glimmer 30B

Answered from the verified figures on this page rather than general guidance.

What is Muse Glimmer 30B's context window?
Muse Glimmer 30B accepts about 131K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Muse Glimmer 30B best for?
Muse Glimmer 30B is a balanced tier from Meta. It suits open-weight deployments, single-gpu serving, cost-sensitive. Template reasoning_strength supports low/medium/high/xhigh, default high. BF16 download is about 60GB; published 17GB/20GB GGUFs need a separate 1.4GB vision projector and optional 1.6GB draft. Meta targets 24GB/32GB hardware by build; actual fit and speed depend on runtime/context. Native Transformers support requires 5.15+. A separate hard output cap remains unknown.
Can I self-host Muse Glimmer 30B?
Muse Glimmer 30B publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.
Model comparison catalogBenchmark library