Skip to main content

    Meta

    Muse Glimmer

    Meta's 30B dense model for local agents, released August 10, 2026 with downloadable Apache 2.0 weights. Accepts text and images and produces text, with a 128K-token context window. Quantized language-model weights fit under 20GB; Meta targets 24GB or 32GB total memory for the weights, working memory, perception encoder and speculative-decoding drafter. Supports tool use, coding and multi-step agent workflows on consumer hardware.

    128K tokens
    Multimodal
    Pro
    New
    Provider
    Meta
    Context
    128K
    Catalog · As of Aug 13, 2026Within 30d
    yno subscription tier
    Pro
    Released
    Aug 10, 2026
    Speed
    Fast
    Reasoning
    Advanced
    Modality
    Multimodal

    Benchmarks

    Quality

    AA Intelligence Index
    18.1points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    49points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    83.5%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    102.55tokens/s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first token
    0.44s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first answer token
    19.94s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown

    API pricing

    API input cost
    $0.35/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $1.50/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: Muse Glimmer (high)

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Open Source
    • Agentic
    • Local Deployment
    • Code
    • Fine-tuning
    • Vision

    Use cases

    • On-prem/local agents
    • Single-GPU deployment
    • Custom fine-tuning
    • Data-sovereign workloads

    Strengths

    • Apache 2.0 weights
    • Text and image input
    • Local agent workflows
    • 24GB/32GB quantized targets

    Best for

    Teams building local agents with downloadable weights and image understanding

    Use Muse Glimmer in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Muse Glimmer?
    Meta's 30B dense model for local agents, released August 10, 2026 with downloadable Apache 2.0 weights. Accepts text and images and produces text, with a 128K-token context window. Quantized language-model weights fit under 20GB; Meta targets 24GB or 32GB total memory for the weights, working memory, perception encoder and speculative-decoding drafter. Supports tool use, coding and multi-step agent workflows on consumer hardware.
    How much does Muse Glimmer cost in yno.ai?
    Muse Glimmer is available on the Pro tier of yno.ai.
    What can Muse Glimmer do?
    Muse Glimmer is best for Teams building local agents with downloadable weights and image understanding. Its main capabilities include Open Source, Agentic, Local Deployment, Code, Fine-tuning, Vision.
    How does Muse Glimmer compare to other models?
    Muse Glimmer excels at Apache 2.0 weights and is recommended for On-prem/local agents, Single-GPU deployment, Custom fine-tuning, Data-sovereign workloads. See related models below.
    How do I use Muse Glimmer in yno.ai?
    Sign up for yno.ai, select Muse Glimmer from the model picker, and start chatting.