Meta Muse Glimmer: 30B open-weight model for local agents. Distilled from Muse Spark with 4-bit quantization, DFlash decoding, and tool failure recovery.
Capabilities, design details, and architectural traits
Muse Glimmer is a 30-billion-parameter dense causal transformer distilled from Meta's closed flagship Muse Spark, purpose-built to run autonomous agentic workflows. Its training combined logit distillation from Muse Spark, mid-training on longer-context and agent-heavy data, and a post-training stage mixing supervised fine-tuning with on-policy distillation and reinforcement learning.
The model is engineered around two technical interventions that make local deployment practical. Weights are compressed to approximately 4-bit precision. Generation is accelerated by a DFlash block-diffusion drafter that proposes entire 16-token blocks in a single forward pass; the main model verifies these proposals in parallel, producing identical output quality at up to 3.1x higher throughput.
| Trait | Detail |
|---|---|
| Distilled from Muse Spark | Logit distillation from the closed flagship during pre-training, followed by on-policy distillation and RL in post-training |
| DFlash speculative decoding | Block-diffusion drafter predicts 16-token blocks; main model verifies in parallel for up to 3.1x speedup with identical output |
| Tool failure recovery | Diagnoses failed or unexpected tool-call results and retries rather than halting the workflow |
| Dedicated perception encoder | ~1.8B ViT-G/14 processes interleaved text and images including screenshots, charts, and documents |
| Controllable effort | Supports adjustable reasoning strength to balance quality against speed |
| Apache 2.0 license | Permits commercial use, modification, and redistribution without the usage restrictions attached to earlier Llama models |
Muse Glimmer works across agentic orchestration patterns including OpenClaw and Hermes Agent, handling function calls with precise schemas across extended multi-step workflows. It is trained on data from more than 100 languages and supports a context length of 131,072+ tokens.
Independent evaluations · Artificial Analysis
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Meta | Anthropic | Anthropic |
| Release Date | August 10, 2026 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | Jan 2026 | May 2026 | - |
| Context & Limits | |||
| Context Window | 131K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | Free Best Input Pricing | $5 | $10 |
| Output Pricing | Free Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | textimagefile | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 35.1 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | 49.0 | 78.0 Best Coding Index | 76.5 |
| Agentic Index | 22.9 | 59.2 Best Agentic Index | 56.6 |
Graduate-level reasoning and expert Q&A evaluation.
Extremely difficult logical reasoning and knowledge.
Logical reasoning over long context windows.
Benchmark scores are independent evaluations sourced from Artificial Analysis. Intelligence, Coding, and Agentic indices reflect composite performance ratings (0–100).
