# How much will this cost?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-much-will-this-cost%2F89146%3E%5C
**Category:** Models\
**Created:** [May 29, 2024, 9:07am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-much-will-this-cost%2F89146 "2024-05-29T09:07:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![dilolo](https://avatars.discourse-cdn.com/v4/letter/d/f07891/32.png) [@dilolo](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdilolo)%5C
**Post date:** [May 29, 2024, 9:07am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-much-will-this-cost%2F89146%2F1 "2024-05-29T09:07:00Z")

</div>

Hello. I have a dataset that contains approximately 100 million sentences (2 billion tokens) not in English. I want to implement a model for generating text. Which is better to choose GPT-2 or Llama 3? Approximately with what parameters server needed and how long will it take to train such a model? (so I can count the costs)