View on OpenRouter DFlash 2: Keep Drafting Parallel
DFlash 2 is the successor to our widely deployed parallel drafter: close to 3× the speed of autoregressive decoding, with the same output. Drafters for Qwen3.8-27B and Meta's Muse Glimmer are out today.
Inco AI
Muse Glimmer 30B
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access.
Specs
Model
- Family
- Muse
- Variant
- Glimmer 30B
- Parameters
- 29.6B
- Weights
- Open
- License
- Apache-2.0
Limits
- Context
- 131,072 tokens
Modalities
- Input
- Text Image
- Output
- Text
Capabilities
- Reasoning
- Yes
- Reasoning control
- Effort levels
- Tool calling
- Yes
- Attachments
- Yes
Dates
- Announced
- 10 Aug 2026
- Released
- 10 Aug 2026
- Knowledge cutoff
- 4 Jan 2026