2 models
DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.
To run DeepSeek-V4-Flash in full precision lossless, run Q3 (UD-Q3_K_M), It is 129 GB. vision tools thinking