Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.
201.7K Pulls 15 Tags Updated 2 weeks ago
779 Pulls 4 Tags Updated 3 weeks ago
The model's safety alignment was removed. It can produce harmful, offensive, or illegal content — use at your own risk and only for research or educational purposes.
287 Pulls 1 Tag Updated 3 weeks ago
pulled from unsloth requant to IQ4_NL, with combined_en_huge as prompt (English + Coding focus)
18 Pulls 1 Tag Updated 1 week ago
Imatrix-quantized GGUF builds of Meta's Muse Glimmer 30B (agentic, multimodal) down to 2-bit for 8–12GB setups — plus the official 17GB base build.
263 Pulls 4 Tags Updated 1 month ago
Runs on an RTX 3070 or better. I used mixed precision, IQ2, and CUDA optimizations.
187 Pulls 1 Tag Updated 1 month ago
a 27.9B vision-language model tuned for Hermes and other agentic workflows.
28 Pulls 1 Tag Updated 1 month ago
22 Pulls 3 Tags Updated 1 month ago
A Muse Glimmer 30B fine-tune for Windows endpoint management: DSC v3, PowerShell 7, and Intune. Matches a dedicated domain fine-tune on accuracy while keeping full tool calling. Refuses legacy DSC 1.1 by design.
2 Pulls 1 Tag Updated 3 weeks ago
6 Pulls 1 Tag Updated 1 month ago