huihui_ai/ deepseek-v3

7,146 1 year ago

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

2 models

deepseek-v3:671b-q3_K
bce4e76cd607 • 319GB • 4K context window •
Text input • 1 year ago
deepseek-v3:671b-q2_K
12b8c735ab7d • 244GB • 4K context window •
Text input • 1 year ago