Sign in
Muse Glimmer logo

Muse Glimmer

Meta · Released Aug 2026

View pricingCompare models
Conditional

Muse Glimmer is Meta's 30B open-weight agentic model, distilled from the closed Muse Spark frontier model and released under Apache 2.0. With 4-bit quantization it runs multi-step tool calling, multimodal reasoning, and failure recovery on a single 24GB consumer GPU without cloud dependencies. It leads its size class on agentic orchestration but trails Qwen3.6-27B on terminal and OS automation — reach for it if you need a capable local agent that stays offline, not if you need independent reproducibility or low-level OS control.

Is it right for you?

Good for

  • Local agentic workflows — runs on a single 24GB consumer GPU at ~20GB quantized, no cloud or internet required
  • Tool use and function calling — reliable schema-based tool invocation across long multi-turn agent sessions
  • Multimodal reasoning — includes a 1.8B ViT-G/14 perception encoder for screenshots, charts, and documents

Not good for

  • Terminal/OS automation — trails Qwen3.6-27B on TerminalBench 2.1 (51.7 vs 60.7) and OSWorld-Verified (65.9 vs 75.6)
  • Reproducibility-critical use — Apache 2.0 weights only; no training data or code released, so the model cannot be independently reproduced

How it performs by task

Agentic task completion

Very Good

Leads Gemma4-31B and Qwen3.6-27B on MCP Atlas (75.5) and DeepSearch QA (74.6); strong multi-step agent reasoning

Code generation

Very Good

SWE-Bench Verified 76.0, SWE-Bench Pro 51.2 — competitive with Qwen3.6-27B on verified, ahead on Pro

Math reasoning

Excellent

AIME 2026 score of 94.7, matching Qwen3.6-27B (94.1) and exceeding Gemma4-31B (89.2)

Terminal/CLI automation

Good

TerminalBench 2.1 score of 51.7 — meaningfully behind Qwen3.6-27B (60.7); not the best fit for shell-heavy agent work

Pricing

Input

Free (open weights)

Output

Free (open weights)

Context

131K tokens

View full pricing

Benchmarks

BenchmarkScoreSource
MCP Atlas (Public)75.5 Source
DeepSearch QA74.6 Source
SWE-Bench Pro51.2 Source
SWE-Bench Verified76.0 Source
TerminalBench 2.151.7 Source
AIME 202694.7 Source
GPQA Diamond (AA)83.5 Source

No verdict changes yet

The clock starts day one. Changes land here as our verdict evolves.

Sources

Verification log

  • Content· No changes

    Automated agent

  • Status· No changes

    Automated agent

How we evaluate