# Llama-2 significantly slower than other models on huggingface

**URL:** <https://discuss.huggingface.co/t/llama-2-significantly-slower-than-other-models-on-huggingface/54170>\
**Category:** 🤗Transformers\
**Created:** [September 8, 2023, 11:09pm UTC](https://discuss.huggingface.co/t/llama-2-significantly-slower-than-other-models-on-huggingface/54170 "2023-09-08T23:09:43Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![surya-narayanan](https://avatars.discourse-cdn.com/v4/letter/s/d2c977/32.png) [@surya-narayanan](https://discuss.huggingface.co/u/surya-narayanan)\
**Post date:** [September 8, 2023, 11:09pm UTC](https://discuss.huggingface.co/t/llama-2-significantly-slower-than-other-models-on-huggingface/54170/1 "2023-09-08T23:09:43Z")

</div>

While running the llama and falcon pipelines, I found that Llama-2 is over 30x slower than falcon for the same size (7b).

Is this something that is to be expected?

---

<div class="post-metadata">

**Author:** ![MaMJ](https://avatars.discourse-cdn.com/v4/letter/m/b5a626/32.png) [@MaMJ](https://discuss.huggingface.co/u/MaMJ)\
**Post date:** [December 25, 2023, 12:32pm UTC](https://discuss.huggingface.co/t/llama-2-significantly-slower-than-other-models-on-huggingface/54170/2 "2023-12-25T12:32:06Z")

</div>

Did you figure out why? Because I found that Llama-2-7b is much slower and requirs smaller batchsize than OPT-6.7b. They are almost the same size.

---

<div class="post-metadata">

**Author:** ![surya-narayanan](https://avatars.discourse-cdn.com/v4/letter/s/d2c977/32.png) [@surya-narayanan](https://discuss.huggingface.co/u/surya-narayanan)\
**Post date:** [May 7, 2024, 10:16pm UTC](https://discuss.huggingface.co/t/llama-2-significantly-slower-than-other-models-on-huggingface/54170/3 "2024-05-07T22:16:57Z")

</div>

haven’t figured it out