deepseek-ai/DeepSeek-R1
35 derivatives checked
- amd/DeepSeek-R1-MXFP4: Different architecture
- unsloth/DeepSeek-R1-GGUF: Quantization
- unsloth/DeepSeek-R1-BF16: Quantization
- bartowski/DeepSeek-R1-GGUF: Quantization
- nvidia/DeepSeek-R1-NVFP4: Different architecture
- unsloth/DeepSeek-R1-GGUF-UD: Quantization
- calcuis/deepseek-r1: Quantization
- raghu1155/DeepSeek-R1-Codegeneration-COT: Adapter
- amd/DeepSeek-R1-MXFP4-ASQ: Different architecture
- mlx-community/DeepSeek-R1-4bit: Different architecture
- silence09/DeepSeek-R1-Small-2layers: Quantization
- XythicK/DeepSeek-R1-GGUF: Quantization
- microsoft/MAI-DS-R1: Quantization
- nvidia/DeepSeek-R1-NVFP4-v2: Different architecture
- tngtech/DeepSeek-TNG-R1T2-Chimera: Full fine-tune
- mlx-community/DeepSeek-R1-3bit: Different architecture
- RedHatAI/DeepSeek-R1-quantized.w4a16: Different architecture
- lmstudio-community/DeepSeek-R1-GGUF: Quantization
- unsloth/DeepSeek-R1: Quantization
- xdatasi/xdata-finetune-deepseek-reason-test-medical: Adapter
- mlx-community/DeepSeek-R1-2bit: Different architecture
- microsoft/MAI-DS-R1-FP8: Full fine-tune
- tngtech/DeepSeek-R1T-Chimera: Partial fine-tune
- QuixiAI/DeepSeek-R1-AWQ: Different architecture
- Barrrrry/DeepSeek-R1-W4AFP8: Different architecture
- TVS759/DeepSeek-TNG-R1T2-Chimera: Full fine-tune
- OPEA/DeepSeek-R1-int2-mixed-sym-inc: Different architecture
- amd/Deepseek-S3_sq_a05_v2_mlperf6_1: Different architecture
- Veltraxor/Veltraxor_1: Identical copy
- centml/DeepSeek-R1-NVFP4-v2-mlpinf: Different architecture