# The model mistralai/Mistral-7B-Instruct-v0.1 is too large to be loaded automatically (14GB \> 10GB)

**URL:** <https://discuss.huggingface.co/t/the-model-mistralai-mistral-7b-instruct-v0-1-is-too-large-to-be-loaded-automatically-14gb-10gb/150632>\
**Category:** Models\
**Created:** [April 15, 2025, 1:38pm UTC](https://discuss.huggingface.co/t/the-model-mistralai-mistral-7b-instruct-v0-1-is-too-large-to-be-loaded-automatically-14gb-10gb/150632 "2025-04-15T13:38:44Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![puru786](https://avatars.discourse-cdn.com/v4/letter/p/e9a140/32.png) [@puru786](https://discuss.huggingface.co/u/puru786)\
**Post date:** [April 15, 2025, 1:38pm UTC](https://discuss.huggingface.co/t/the-model-mistralai-mistral-7b-instruct-v0-1-is-too-large-to-be-loaded-automatically-14gb-10gb/150632/1 "2025-04-15T13:38:44Z")

</div>

I was using the model with the inference api , Initially it was working fine but after 2-3 hours in the evening i started to get this error.  
Hoe can i resolve and use the model with free Access token.

---

<div class="post-metadata">

**Author:** ![Injaz](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/injaz/32/45458_2.png) [@Injaz](https://discuss.huggingface.co/u/Injaz)\
**Post date:** [April 15, 2025, 1:56pm UTC](https://discuss.huggingface.co/t/the-model-mistralai-mistral-7b-instruct-v0-1-is-too-large-to-be-loaded-automatically-14gb-10gb/150632/2 "2025-04-15T13:56:20Z")

</div>

The same Happened with Qwen 2.5 VL 7B and i think they have removed it from hugging face serverless service via hugging face Inference API , try different provider for the API call or use a dedicated server (this worked for me).

---

<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 15, 2025, 2:38pm UTC](https://discuss.huggingface.co/t/the-model-mistralai-mistral-7b-instruct-v0-1-is-too-large-to-be-loaded-automatically-14gb-10gb/150632/3 "2025-04-15T14:38:03Z")

</div>

I think this will only be fixed if someone applies for it.

 ![mistralinference](https://us1.discourse-cdn.com/hellohellohello/original/3X/0/5/057d29ad7291fd73f57692dcc124b7ea4508bca1.png)