# Unable to run quantized model with Zero GPU space

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-run-quantized-model-with-zero-gpu-space%2F91598%3E%5C
**Category:** Spaces\
**Created:** [June 11, 2024, 5:44pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-run-quantized-model-with-zero-gpu-space%2F91598 "2024-06-11T17:44:35Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tanyuzhou](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/tanyuzhou/32/28101_2.png) [@tanyuzhou](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftanyuzhou)%5C
**Post date:** [June 11, 2024, 5:44pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Funable-to-run-quantized-model-with-zero-gpu-space%2F91598%2F1 "2024-06-11T17:44:35Z")

</div>

Hi guys! I am trying to deploy a 4-bit llm model in a Zero GPU space, and encountered problems when load the pretrained model outside the method with @spaces.GPU decoration.

I posted a discussion on zero-gpu org, is anybody can help me with this issue?

[Zero GPU does not support 4-bit quantization with bitsandbytes?](https://huggingface.co/spaces/zero-gpu-explorers/README/discussions/71)