# 如何将模型转换为gguf格式？

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgguf%2F88663%3E%5C
**Category:** Beginners\
**Created:** [May 27, 2024, 1:52am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgguf%2F88663 "2024-05-27T01:52:05Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![sfhehfswfh](https://avatars.discourse-cdn.com/v4/letter/s/f6c823/32.png) [@sfhehfswfh](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsfhehfswfh)%5C
**Post date:** [May 27, 2024, 1:52am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgguf%2F88663%2F1 "2024-05-27T01:52:05Z")

</div>

How to convert models microsoft/Phi-3-vision-128k-instruct to GGUF format. One for Windows and macOS (silicon and intel), The original installation method never worked on my end, I needed a more convenient method. interchip machine.

---

<div class="post-metadata">

**Author:** ![Andynsn](https://avatars.discourse-cdn.com/v4/letter/a/e9c0ed/32.png) [@Andynsn](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAndynsn)%5C
**Post date:** [July 26, 2024, 8:50am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fgguf%2F88663%2F2 "2024-07-26T08:50:40Z")

</div>

use llama.cpp， for example，python convert-hf-to-gguf.py Qwen/Qwen1.5-7B-Chat --outfile models/7B/qwen1\_5-7b-chat-fp16.gguf