AI/TLDR

HUST + Huawei · 2026-07-29 · notable

TurboVLA — 0.2B robot policy runs at 32 Hz on RTX 4090 in under 1 GB VRAM

TurboVLA is a 0.2B-parameter vision-language-action model that swaps the usual V→L→A pipeline for a direct V+L→A path, hitting 97.7% on LIBERO at 32 Hz on an RTX 4090 with under 1 GB VRAM.

TurboVLA repository card on GitHub showing the project title and a real-time robot manipulation demo.

A tiny vision-language-action model that keeps up with a real robot on a gaming GPU.

Key specs

Parameters0.2B
Vram<1 GB
Rate32 Hz
Libero avg97.7%

What is it?

TurboVLA is an open-source vision-language-action model for robot manipulation from Huazhong University of Science and Technology and Huawei. The 0.2B-parameter policy runs at 32 Hz on a single RTX 4090 in under 1 GB of VRAM, and posts 97.7% average success on the LIBERO benchmark.

How does it work?

Most VLAs route the camera through a large language model before predicting an action (V→L→A). TurboVLA drops that path and encodes vision and language in parallel, exchanges information through a lightweight bidirectional cross-attention block, and predicts action chunks with a compact decoder. Inference is 31.2 ms per step, so the loop keeps up with a 30 Hz control rate on a consumer GPU.

Why does it matter?

Real-time robot control usually needs a workstation-grade GPU or a distilled policy. TurboVLA runs the full policy in real time on a laptop-class card with room to spare, which lowers the bar for hobbyist and university robotics groups that already have a 40-series GPU. The paper also reports 60.2% on RoboTwin 2.0 bimanual tasks.

Who is it for?

Robotics researchers and hobbyists running LIBERO / RoboTwin on a single RTX-40 GPU.

Try it

git clone https://github.com/H-EmbodVis/TurboVLA

Sources · 3 outlets

Tags

  • paper
  • algorithm
  • vision-language-action
  • vla
  • robotics
  • embodied-ai
  • libero
  • edge-inference
  • huawei
  • hust
  • apache-2-0

← All releases · Learn AI