Llama2模型量化结果地址

TheBlokeAI在Llama2发布几个小时就发布了量化版本，速度真快~

<center>![](https://www.datalearner.com/resources/blog_images/55ffef19-139e-4648-9fc5-84c29f5335e1.png)</center>
<center></center>

|  量化版本名称 | 量化模型链接  | int-4量化|最大内存|
| ------------ | ------------ |
| Llama-2-70B-GPTQ  |https://huggingface.co/TheBloke/Llama-2-70B-GPTQ   | 35.33 GB ||
| Llama-2-70B-chat-GPTQ  | https://huggingface.co/TheBloke/Llama-2-70B-chat-GPTQ  | 35.33 GB ||
| Llama-2-13B-chat-GPTQ  | https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ  | 7.26 GB | |
| Llama-2-13B-chat-GGML |  https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML |7.32 GB | 9.82 GB |
| Llama-2-13B-GPTQ | https://huggingface.co/TheBloke/Llama-2-13B-GPTQ | 7.26 GB | |
| Llama-2-13B-GGML | https://huggingface.co/TheBloke/Llama-2-13B-GGML| 	7.32 GB | 9.82 GB |
| Llama-2-7B-GGML  |  https://huggingface.co/TheBloke/Llama-2-7B-GGML | 3.79 GB | 6.29 GB |
| Llama-2-7B-GPTQ  | https://huggingface.co/TheBloke/Llama-2-7B-GPTQ  | 3.90 GB | |
| Llama-2-7B-Chat-GGML | https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML | 3.79 GB| 6.29 GB |
| Llama-2-7b-Chat-GPTQ |https://huggingface.co/TheBloke/Llama-2-7b-Chat-GPTQ| 3.90 GB | | |

Llama2模型量化结果地址

欢迎大家关注DataLearner官方微信，接受最新的AI技术推送

相关博客

最热博客