# TGI Model Question

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftgi-model-question%2F55935%3E%5C
**Category:** 🤗Hub\
**Created:** [September 21, 2023, 10:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftgi-model-question%2F55935 "2023-09-21T22:22:03Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ahmkhan](https://avatars.discourse-cdn.com/v4/letter/a/a88e57/32.png) [@Ahmkhan](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAhmkhan)%5C
**Post date:** [September 21, 2023, 10:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftgi-model-question%2F55935%2F1 "2023-09-21T22:22:03Z")

</div>

Does TGI Model ([GitHub - huggingface/text-generation-inference: Large Language Model Text Generation Inference](https://github.com/huggingface/text-generation-inference)) has any metric or api to know time taken to generate first token?

Also, I receive below error when my parameter sends stream=true - Does decoder\_input\_detail works only with stream = false?

`decoder_input_details` == true is not supported when streaming tokens"