trillionlabs / Gravity-30B-A5B-Base
Text Generation30B2111Updated Sep 10, 2026
Downloads
211
Likes
1
Last updated
Sep 10, 2026
License
apache-2.0
Gravity-30B-A5B-Base is a pretrained sparse Mixture-of-Experts (MoE) language model by Trillion Labs and the Lunit Consortium. It features 29.56B total parameters with 5.34B active parameters per token and a native 128K context window.
Tasks & library
- text generation
- transformers
Tags
- transformers
- gravity_moe
- text-generation
- moe
- mixture-of-experts
- gravity
Technical specifications
Parameters30B
Librarytransformers
Languagesen, ko
Licenseapache-2.0