--- datasets: - StarVLA/RoboTwin-Clean language: - en license: other license_name: dinov3-license license_link: https://huggingface.co/H-EmbodVis/TurboVLA/blob/main/DINOv3_LICENSE.md pipeline_tag: robotics tags: - robotics - embodied-ai - vision-language-action - robot-manipulation - pytorch - safetensors - dinov3 - libero - robotwin arxiv: "2607.27205" ---

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Paper Project page GitHub repository DINOv3 License
Hengyi Xie1*, Chenfei Yao1*, Xianjin Wu1, Xuanyang Xi2, Yiping Tang2, Di Xu2, Yingying Zhu1, Dingkang Liang1†, Xiang Bai1, Han Ding1
1 Huazhong University of Science and Technology, China
2 Huawei Technologies Co. Ltd, China
* Equal contribution, listed alphabetically by surname. † Project lead.
## 🔍 Overview **TurboVLA** is a real-time vision-language-action model for robotic manipulation. It replaces the conventional LLM-centric vision-to-language-to-action pathway with a direct vision-plus-language-to-action design: visual observations and language instructions are encoded independently, exchanged through lightweight bidirectional interaction, and decoded into continuous action chunks. This repository contains the official TurboVLA checkpoints for the **LIBERO** and **RoboTwin 2.0** evaluations.
Abstract Vision-language-action (VLA) models commonly adopt an LLM-centric V → L → A pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional V → L → A pathway as a direct V + L → A mapping. Instead of using a large language model as the central interface between perception and action, TurboVLA independently encodes visual observations and language instructions, directly exchanges information between them through lightweight bidirectional vision-language interaction, and predicts continuous action chunks with a compact decoder. This simple design constructs task-conditioned representations directly from visual and linguistic features, significantly reducing the computational and memory costs of VLA inference. On LIBERO, TurboVLA achieves 97.7% average success with only 0.2B parameters, 31.2 ms inference latency, and 0.9 GB inference VRAM on a consumer-grade RTX 4090, matching or outperforming substantially larger VLA policies. These results establish TurboVLA as a simple and effective alternative to the prevailing LLM-centric VLA paradigm, offering a new perspective on how vision, language, and action can be connected for efficient robotic manipulation.
### ✨ Key Ideas - Direct vision-plus-language-to-action modeling without an LLM-centric action pathway. - Independent DINOv3 visual and BERT language encoders with lightweight bidirectional interaction. - Compact action-chunk decoders for low-latency and memory-efficient inference. - Official checkpoints for both LIBERO and RoboTwin 2.0. ## 🎯 Task, Inputs, and Outputs TurboVLA predicts continuous robot action chunks from synchronized multi-view RGB observations, a natural-language instruction, and the robot proprioceptive state. | Benchmark | Inputs | Output | Action horizon | Visual encoder | | --- | --- | --- | ---: | --- | | LIBERO | Two RGB views, language instruction, robot state | 7-D continuous actions | 12 | DINOv3 ViT-B | | RoboTwin 2.0 | Three 224 x 224 RGB views, language instruction, 14-D robot state | 14-D absolute joint-position actions | 50 | DINOv3 ViT-L | ## 📦 Released Checkpoints ### LIBERO The LIBERO model was jointly trained on all four suites in a single mixed-suite training run. The released evaluation uses the following suite-specific checkpoints: | Suite | Evaluation name | Checkpoint | | --- | --- | --- | | LIBERO-Object | `libero_object` | `checkpoints/libero/object.pth` | | LIBERO-Goal | `libero_goal` | `checkpoints/libero/goal.pth` | | LIBERO-Spatial | `libero_spatial` | `checkpoints/libero/spatial.pth` | | LIBERO-Long | `libero_10` | `checkpoints/libero/long.pth` | The LIBERO files are model-state-only PyTorch checkpoints. Optimizer and scheduler states were removed; the released `model_state_dict` tensors are unchanged and are compatible with the official TurboVLA loader. ### RoboTwin 2.0 | Training data | Weights | Checkpoint | | --- | --- | --- | | RoboTwin Clean, 50 tasks | EMA | `checkpoints/robotwin/` | ## 🛠️ Usage You can download the complete model repository using either the Hugging Face CLI or the Python SDK. **Option 1: Hugging Face CLI (Recommended)** ```bash pip install -U huggingface_hub hf download H-EmbodVis/TurboVLA --local-dir TurboVLA-model ``` **Option 2: Python SDK** ```python from huggingface_hub import snapshot_download snapshot_download( repo_id="H-EmbodVis/TurboVLA", repo_type="model", local_dir="TurboVLA-model", ) ``` TurboVLA is a custom PyTorch VLA implementation and is not directly loadable with `transformers.AutoModel.from_pretrained()`. For installation and evaluation instructions, use the [official GitHub repository](https://github.com/H-EmbodVis/TurboVLA). ## 📂 Repository Contents | Path | Description | | --- | --- | | `checkpoints/libero/*.pth` | Four LIBERO suite-specific evaluation checkpoints | | `checkpoints/robotwin/*.safetensors` | RoboTwin 2.0 EMA checkpoint | | `libero_all4_stats.json` | Mixed-suite LIBERO normalization statistics | | `config.yaml` | RoboTwin model and inference configuration | | `dataset_statistics.json` | RoboTwin state and action normalization statistics | | `config.json` | Hugging Face model metadata and checkpoint index | | `CHECKSUMS.sha256` | SHA-256 checksums for all released checkpoints | | `DINOv3_LICENSE.md` | DINOv3 terms applicable to the released checkpoint parameters | | `LICENSE` | Apache-2.0 license for the TurboVLA project code | ## ⚖️ License The TurboVLA source code is released under Apache-2.0. The released checkpoints contain parameters derived from DINOv3 and are distributed subject to the included [DINOv3 License](DINOv3_LICENSE.md). Users must comply with all applicable third-party license terms. ## 📖 Citation If you find this work useful, please consider citing: ```bibtex @article{xie2026turbovla, title = {TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM}, author = {Xie, Hengyi and Yao, Chenfei and Wu, Xianjin and Xi, Xuanyang and Tang, Yiping and Xu, Di and Zhu, Yingying and Liang, Dingkang and Bai, Xiang and Ding, Han}, journal = {arXiv preprint arXiv:2607.27205}, year = {2026} } ```