# Loading a local llm model with mlx-lm

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floading-a-local-llm-model-with-mlx-lm%2F88611%3E%5C
**Category:** Beginners\
**Created:** [May 26, 2024, 5:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floading-a-local-llm-model-with-mlx-lm%2F88611 "2024-05-26T17:30:50Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![villager222](https://avatars.discourse-cdn.com/v4/letter/v/35a633/32.png) [@villager222](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fvillager222)%5C
**Post date:** [May 26, 2024, 5:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floading-a-local-llm-model-with-mlx-lm%2F88611%2F1 "2024-05-26T17:30:50Z")

</div>

I have been using this on my MacBook Pro for a couple of months with no problems. I returned back this week and this code fails:

```python
from mlx_lm import load
model_filename = '/Users/myname/llm_models/gemma/gemma-7b-it'
model, tokenizer = load(model_filename)

```

error message:  
HFValidationError: Repo id must be in the form ‘repo\_name’ or ‘namespace/repo\_name’: ‘/Users/myname/llm\_models/gemma/gemma-7b-it’. Use `repo_type` argument if needed.

Would appreciate any advice in getting this going again.