---
title: "Discussion on \"OpenVLA: How a 7B Open-Source Model Beat a 55B Closed-Source One\" | Hashnode"
description: "Discussion on \"OpenVLA: How a 7B Open-Source Model Beat a 55B Closed-Source One\". Llama 2 + DINOv2 + SigLIP — 16.5 points higher than RT-2-X, fine-tunable on a single GPU"
url: "https://hashnode.com/posts/blog-openvla-en/69dec0fa9b87d8aee5a354cc"
---

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

Discussion

# [OpenVLA: How a 7B Open-Source Model Beat a 55B Closed-Source One](https://telos-robotics.hashnode.dev/blog-openvla-en?utm_source=hashnode&utm_medium=feed)

Llama 2 + DINOv2 + SigLIP — 16.5 points higher than RT-2-X, fine-tunable on a single GPU

Apr 14 · 7 min read · telos-robotics.hashnode.dev  
Read the article

-   [#llm](https://hashnode.com/tag/llm)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#open-source](https://hashnode.com/tag/open-source)
-   [#robotics](https://hashnode.com/tag/robotics)
-   [#vla](https://hashnode.com/tag/vla)

## Written by

[telos](https://hashnode.com/@telos)

@telos · Seoul, South Korea

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

I build robots for a living. Not in simulation. Not in a lab. On the floor, with real hardware, real failure modes, and real deadlines. My work spans the full stack of modern robotics: embedded systems firmware, autonomous navigation, and the end-to-end pipeline for Vision-Language-Action (VLA) model development — dataset collection, training, inference optimization, and sim-to-real transfer. I've worked hands-on with platforms from Unitree, Deep Robotics, Dexmate, and Robotis, among others. Each one teaches you something different about the gap between what models promise and what robots actually do.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.