---
license: apache-2.0
base_model: allenai/MolmoAct2-LIBERO
tags:
  - robotics
  - vision-language-action
  - tensorrt
  - jetson
  - molmoact2
  - libero
  - edge-inference
---

# MolmoAct2 LIBERO engines for Jetson AGX Thor

Prebuilt TensorRT engines for running
[`allenai/MolmoAct2-LIBERO`](https://huggingface.co/allenai/MolmoAct2-LIBERO)
with [vla-edge](https://github.com/Agents2AgentsAI/vla-edge). This is the
configuration used for our 2,000-episode LIBERO evaluation.

With the FP8 vision engine enabled, it scored **97.2% overall**, matching the
MolmoAct2 paper result within sampling noise. See the
[performance writeup](https://agents2agents.ai/blog/molmoact2-jetson-thor) for
the methodology and per-suite results.

## Download and verify

This repository is about 10.5 GB.

```bash
hf download agents2agents/MolmoAct2-LIBERO-Jetson-Thor \
  --local-dir vla-edge-libero
cd vla-edge-libero
python -c "from vla_edge.backends.tensorrt import artifacts; \
artifacts.check_compatible('.'); artifacts.verify_checksums('.'); \
print('bundle verified')"
```

## Run

```bash
vla-edge-serve --embodiment libero --backend tensorrt \
  --engine-dir /path/to/vla-edge-libero/libero --fast-vision
```

The public API expects two images named `image` and `wrist_image`, plus the
eight-value LIBERO state vector. The startup warmup executes every compiled
stage.

## Hardware and contents

These plans require an NVIDIA Jetson AGX Thor Developer Kit with JetPack R39
rev 2.1 and TensorRT 10.16.2.10.

```text
libero/             fixed 704-token engines and FP8 vision option
host/libero/        processor, normalization, embeddings, and flow weights
MANIFEST.json       compatibility requirements and checksums
```

Serving this bundle is local and does not download the upstream checkpoint.

## License

Apache-2.0. See [LICENSE](LICENSE) and [NOTICE](NOTICE).

The plans embed weights from `allenai/MolmoAct2-LIBERO`, released by the Allen
Institute for AI under Apache-2.0. The conversion changes execution, not the
checkpoint parameters.