---
title: "Discussion on \"TensorRT INT8 vs FP16 on RF-DETR, Measured on an RTX 5090\" | Hashnode"
description: "Discussion on \"TensorRT INT8 vs FP16 on RF-DETR, Measured on an RTX 5090\". A calibrated TensorRT INT8 build of RF-DETR put 0 layers in INT8 on an RTX 5090. Measured INT8, FP16, CPU quantization and distillation side by side."
url: "https://hashnode.com/posts/tensorrt-int8-vs-fp16-on-rf-detr-measured-on-an-rtx-5090/6adbccf2d53c4a369c38ed3c"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [TensorRT INT8 vs FP16 on RF-DETR, Measured on an RTX 5090](https://khadimhussain0.hashnode.dev/tensorrt-int8-vs-fp16-on-rf-detr-measured-on-an-rtx-5090?utm_source=hashnode&utm_medium=feed)

A calibrated TensorRT INT8 build of RF-DETR put 0 layers in INT8 on an RTX 5090. Measured INT8, FP16, CPU quantization and distillation side by side.

Oct 23 · 11 min read · khadimhussain0.hashnode.dev  
Read the article

-   [#tensorrt](https://hashnode.com/tag/tensorrt)
-   [#computer-vision](https://hashnode.com/tag/computer-vision)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)

## Written by

[Khadim Hussain](https://hashnode.com/@khadimxai)

@khadimxai · Islamabad, Pakistan

  
[View profile](https://hashnode.com/@khadimxai)

AI engineer building AI agents, LLM and RAG systems, and computer vision. I write about what I test at khadim.tech.

I build AI agents, LLM and RAG systems, and computer vision pipelines, and I test new AI tools hands-on before writing about them. Top Rated Plus on Upwork. Write-ups and contact: https://khadim.tech

## Responses

Markdown supported · ⌘↵ to post

No responses yet.