| --- | |
| license: apache-2.0 | |
| license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE | |
| pipeline_tag: text-generation | |
| tags: | |
| - Qwen3 | |
| - gptq | |
| - int4 | |
| - 量化 | |
| - vLLM | |
| base_model: | |
| - Qwen/Qwen3-30B-A3B | |
| base_model_relation: quantized | |
| # 通义千问Qwen3-30B-A3B-GPTQ-Int8量化 | |
| 基础模型 [通义千问3-30B-A3B](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B) | |
| ### 最近更新 | |
| ``` | |
| 2025-05-08 | |
| fix (model.layers.*.mlp.gate) are not quantized | |
| ``` | |
| ### 依赖 | |
| ``` | |
| vllm==0.8.5 | |
| ``` | |
| SDK下载 | |
| ```bash | |
| #安装ModelScope | |
| pip install modelscope | |
| ``` | |
| ```python | |
| #SDK模型下载 | |
| from modelscope import snapshot_download | |
| model_dir = snapshot_download('JunHowie/Qwen3-30B-A3B-GPTQ-Int8') | |
| ``` | |
| Git下载 | |
| ``` | |
| #Git模型下载 | |
| git clone https://www.modelscope.cn/JunHowie/Qwen3-30B-A3B-GPTQ-Int8.git | |
| ``` | |
| <p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p> |