# Want to use CPU for falcon7b

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwant-to-use-cpu-for-falcon7b%2F44174%3E%5C
**Category:** Beginners\
**Created:** [June 22, 2023, 11:04am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwant-to-use-cpu-for-falcon7b%2F44174 "2023-06-22T11:04:03Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tolkoton](https://avatars.discourse-cdn.com/v4/letter/t/3bc359/32.png) [@tolkoton](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftolkoton)%5C
**Post date:** [June 22, 2023, 11:04am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwant-to-use-cpu-for-falcon7b%2F44174%2F1 "2023-06-22T11:04:03Z")

</div>

My system runs out of memory on GPU. But I want just to test if it works and want to load it on CPU. How do I do that?  
Adding ‘’‘device = torch.device(‘cpu’)’‘’ before loading model doesn’t help  
It crashes here:

```auto
model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True,
)

```