# Chapter 2 questions

**URL:** <https://discuss.huggingface.co/t/chapter-2-questions/6799>\
**Category:** Course\
**Created:** [June 14, 2021, 2:51pm UTC](https://discuss.huggingface.co/t/chapter-2-questions/6799 "2021-06-14T14:51:48Z")\
**Posts on this page:** 1\
**Showing post:** 101

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [April 29, 2025, 12:32am UTC](https://discuss.huggingface.co/t/chapter-2-questions/6799/101 "2025-04-29T00:32:26Z")

</div>

Yea. Only on documents or on Hugging Face Discord.

> [@Avoiding the usage of HfApiModel and using local model - \`smolagents\`](https://discuss.huggingface.co/t/avoiding-the-usage-of-hfapimodel-and-using-local-model-smolagents/152711/2):
>
> There are several methods, but you can use TransformersModel instead of HfApiModel and it will work. When using large models, powerful GPUs are required, so please be careful. Well, I think SmolLM below will work with about 1GB of VRAM… Also, Ollama is faster and uses less VRAM, but I think it will be a little difficult to set up (compared to TransformersModel…). from smolagents import TransformersModel model = TransformersModel(model\_id="HuggingFaceTB/SmolLM-135M-Instruct")

---

_[View the full topic](https://discuss.huggingface.co/t/chapter-2-questions/6799)._