DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
398.5K Pulls 2 Tags Updated 4 weeks ago
DeepSeek-V4.1-Flash is an advanced tool designed to enhance search capabilities, providing users with faster and more accurate results.
8,376 Pulls 1 Tag Updated 2 days ago
A customized DeepSeek-V4-Pro
27 Pulls 1 Tag Updated 3 weeks ago
No Oficial 29 t/s en 8 VRAM - Calidad a escala fronteriza como GPT-5.5, DeepSeek-V4-pro y Kimi-K2.6.
981 Pulls 1 Tag Updated 1 month ago
787 Pulls 1 Tag Updated 3 months ago
391 Pulls 1 Tag Updated 3 months ago
deepseek v4 pro on max reasoning using the official system prompt
87 Pulls 1 Tag Updated 1 month ago
122 Pulls 1 Tag Updated 3 months ago
85 Pulls 1 Tag Updated 1 month ago
31 Pulls 1 Tag Updated 3 months ago
pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
3,687 Pulls 1 Tag Updated 3 months ago
To run DeepSeek-V4-Flash in full precision lossless, run Q4 (UD-Q4_K_XL), It is 155GB. vision tools thinking
690 Pulls 1 Tag Updated 1 month ago
To run DeepSeek-V4-Flash in full precision lossless, run IQ1 (UD-IQ1_S), It is 82GB. vision tools thinking
296 Pulls 1 Tag Updated 1 month ago
To run DeepSeek-V4-Flash in full precision lossless, run Q3 (UD-Q3_K_M), It is 129 GB. vision tools thinking
144 Pulls 1 Tag Updated 1 month ago
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.
1,407 Pulls 5 Tags Updated 1 year ago