## 模型文件规格说明

| 文件名 | 量化类型 | 文件大小 | 描述 |
| -------- | ---------- | --------- | ----------- |
| [DeepSeek-R1-Medical-COT-Q2_K.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q2_K.gguf) | Q2_K | 3.179 GB | 最小体积，显著质量损失 - 不推荐多数场景使用 |
| [DeepSeek-R1-Medical-COT-Q3_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | 极小体积，高质量损失 |
| [DeepSeek-R1-Medical-COT-Q3_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | 极小体积，高质量损失 |
| [DeepSeek-R1-Medical-COT-Q3_K_L.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | 小体积，明显质量损失 |
| [DeepSeek-R1-Medical-COT-Q4_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q4_0.gguf) | Q4_0 | 4.661 GB | 传统格式；小体积，极高质量损失 - 建议优先使用Q3_K_M |
| [DeepSeek-R1-Medical-COT-Q4_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | 小体积，较大质量损失 |
| [DeepSeek-R1-Medical-COT-Q4_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | 中等体积，平衡质量 - 推荐 |
| [DeepSeek-R1-Medical-COT-Q5_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q5_0.gguf) | Q5_0 | 5.599 GB | 传统格式；中等体积，平衡质量 - 建议优先使用Q4_K_M |
| [DeepSeek-R1-Medical-COT-Q5_K_S.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | 大体积，低质量损失 - 推荐 |
| [DeepSeek-R1-Medical-COT-Q5_K_M.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | 大体积，极低质量损失 - 推荐 |
| [DeepSeek-R1-Medical-COT-Q6_K.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q6_K.gguf) | Q6_K | 6.596 GB | 超大体积，几乎无损质量 |
| [DeepSeek-R1-Medical-COT-Q8_0.gguf](https://huggingface.co/tensorblock/DeepSeek-R1-Medical-COT-GGUF/blob/main/DeepSeek-R1-Medical-COT-Q8_0.gguf) | Q8_0 | 8.541 GB | 超大体积，完全无损质量 - 不推荐 |

## 下载指南

### 命令行方式

首先安装Huggingface客户端：
```shell
pip install -U "huggingface_hub[cli]"

下载单个模型文件到本地目录：

huggingface-cli download tensorblock/DeepSeek-R1-Medical-COT-GGUF --include "DeepSeek-R1-Medical-COT-Q2_K.gguf" --local-dir 本地目录路径

批量下载匹配模式的模型文件（例如所有Q4_K开头的gguf文件）：

huggingface-cli download tensorblock/DeepSeek-R1-Medical-COT-GGUF --local-dir 本地目录路径 --local-dir-use-symlinks False --include='*Q4_K*gguf'