전체 검색

AI 모델 84759

• vit_large_patch14_clip_224.openai_ft_in12k_in1k↗

  timm

• DeepSeek-V4-Flash-Vision-Exp-GGUF↗

  unsloth

  To run DeepSeek-V4-Flash-Vision-Exp in full precision lossless, run Q8 (UD-Q8_K_XL), which is 162GB and only 7GB bigger than Q4 (UD-Q4_K_XL). See our DeepSeek-V4 guide for quantization analysis and instructions. You can now run DeepSeek-V4-Flash-Vision-Exp in Unsloth Studio with toggles for High and Max thinking. > Image input requires llama.cpp b10766 or later, which is the first release containing the DeepSeek-V4 vision support from #28133 and #28154. We are excited to introduce **DeepSeek-V4-Flash-Vision-Exp**, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

• Llama-4-Maverick-17B-128E-Instruct-GGUF-UD↗

  unsloth

• RealVisXL_V4.0↗

  votepurchase

• epiCPhotoGasm↗

  Yntec

• modernbert-tr-pii-ner↗

  ytu-ce-cosmos

• qwen1.5-moe-tiny-random↗

  yujiepan

• BiRefNet_512x512↗

  ZhengPeng7

• swin_tiny_patch4_window7_224.CTransPath↗

  1aurent

• Llama3-OpenBioLLM-70B↗

  aaditya