Command Palette
Search for a command to run

Muse Glimmer 30B

by Meta

Specifications

Input
Output
Context window
128K tokens
Released
Aug 2026

Performance

Speed
112 t/s
TTFT
Latency
95 ms
Intelligence

Pricing

Input
€0.20
per 1M tokens
Output
€1.00
per 1M tokens
€0.05 cache hit

About this model

Meta Muse Glimmer 30B is a 29.6B parameter dense causal transformer with a dedicated 1.8B perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. It supports multimodal input (text and interleaved images) with 131K+ context, multi-step reasoning, reliable tool use with precise schemas, and failure recovery. The model achieves 76.0% on SWE-Bench Verified, 94.7% on AIME 2026, 83.5% on GPQA Diamond, and 75.5% on MCP Atlas. Optimized for local deployment with quantization and DFlash speculative decoding, it runs within a 24GB VRAM envelope. Available under Apache 2.0 license.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning
Hybrid Default on

Knowledge horizon

Knowledge cutoff Jan 2026
Released Aug 2026
Today
Training to release 7 mo Since release 0 mo

See also

Add Model to Comparison
Search for a model to add
Command Palette
Search for a command to run