milkey/
deepseek-v3-UD

2,004 7 months ago

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

3 models

deepseek-v3-UD:IQ1_S
9ce3ae0fb95d • 140GB • 4K context window •
Text input • 7 months ago
deepseek-v3-UD:IQ1_M
42cef8be6c74 • 155GB • 4K context window •
Text input • 7 months ago
deepseek-v3-UD:IQ2_XXS
745eb9f86c04 • 196GB • 4K context window •
Text input • 7 months ago