ConicCat / GL-Marvin-32k-32B
Text Generation33B1004Updated Jul 12, 2025
Downloads
100
Likes
4
Last updated
Jul 12, 2025
License
apache-2.0
32K context requires only 2GB VRAM, so you can fit Q4KM + 32k context on a single 24GB GPU, best in class for 32B dense models.
Tasks & library
- text generation
- transformers
Tags
- transformers
- glm4
- text-generation
- unsloth
- trl
- conversational