org/
deepseek-v3-fast

85 7 months ago

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

Models

View all →

4 models

deepseek-v3-fast:latest

244GB · 4K context window · Text · 7 months ago

deepseek-v3-fast:Q2_K_L

latest

244GB · 4K context window · Text · 7 months ago

deepseek-v3-fast:Q2_K_XS

221GB · 4K context window · Text · 7 months ago

deepseek-v3-fast:Q4_K_M

404GB · 4K context window · Text · 7 months ago

Readme

No readme