deepseek-ai/DeepSeek-V4-Pro
23 derivatives checked
- nvidia/DeepSeek-V4-Pro-NVFP4: Quantization
- sgl-project/DeepSeek-V4-Pro-FP8: Different architecture
- NagusameCS/ultratensor-models: Not comparable yet
- nvidia/DeepSeek-V4-Pro-nvfp4-DSpark: Quantization
- inference-optimization/DeepSeek-V4-Pro-0.5B-A0.37B: Different architecture
- mlx-community/DeepSeek-V4-Pro: Quantization
- amd/DeepSeek-V4-Pro-MXFP4: Quantization
- yujiepan/deepseek-v4-tiny-random: Different architecture
- yujiepan/deepseek-v4-fp4-fp8-tiny-random: Different architecture
- amd/DeepSeek-V4-Pro-NVFP4: Quantization
- teamblobfish/DeepSeek-V4-Pro-GGUF: Not comparable yet
- inferencerlabs/DeepSeek-V4-Pro-MTP-MLX: Quantization
- DevQuasar/deepseek-ai.DeepSeek-V4-Pro-GGUF: Not comparable yet
- AxionML/DeepSeek-V4-Pro-NVFP4: Quantization
- wdfgyuagguf/DeepSeek-V4-Pro-NVFP4-FREE: Quantization
- unsloth/DeepSeek-V4-Pro: Identical copy
- canada-quant/DeepSeek-V4-Pro-NVFP4-FP8-MTP: Quantization
- silence09/DeepSeek-V4-Pro-Tiny: Different architecture
- RedHatAI/DeepSeek-V4-Pro-NVFP4-FP8: Quantization
- yujiepan/deepseek-v4-bf16-tiny-random: Different architecture
- batiai/DeepSeek-V4-Pro-GGUF: Not comparable yet
- livadies/DeepSeek-V4-Pro-Ghetto-Edition-MoE-Rank-64: Different architecture
- INCModel/DeepSeek-V4-Pro-MXFP4-Mixed-CT-AutoRound: Quantization
157 other repos hold byte-for-byte identical weight files.