LLM
GA
Open weights
Muse Glimmer 30B
Local agent workflows
Release2026-08
Context131K
Max output—
Parameters29.6B
Local / VRAM24–32 GB
LicenseOpen weights
Overview
Muse Glimmer 30B is a model in the LLM category from Meta AI. It was released in 2026-08. The vendor is based in US. Best for: Local agent workflows.
Hardware: Meta targets 24/32 GB quantized, 64 GB full precision.
Strengths
- Apache-2.0
- Image input
- 24 GB class
Limits
- Smaller ecosystem than Llama 4
- 131K context
Specifications
| Vendor | Meta AI |
|---|---|
| Category | LLM |
| Release | 2026-08 |
| Status | GA |
| License | Open weights |
| License name | Apache-2.0 |
| Commercial use | Allowed |
| Parameters | 29.6B |
| Architecture | dense transformer |
| Context window | 131K |
| Input modalities | Text, Image |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 24–32 GB |
| System RAM | 32–64 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | High |
| Vendor country | US |
| Vendor type | Frontier lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 24–32 GB. Approximate system RAM: 32–64 GB. API access is available.