A compact 450M-parameter VLA from Hugging Face, pretrained on community-collected LeRobot datasets and sized for fine-tuning and inference on consumer GPUs.
lerobot/pi05_base
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelVision-language-action3.6B paramsEst. 24 GB GPUEstimated minimum compute for inference: Desktop GPU with about 24 GB of memory. Not a benchmark.Gemma termsSingle armBimanualMobile base
About
LeRobot's port of the Physical Intelligence pi0.5 base model, which is co-trained on web and multi-robot data to generalize better to unfamiliar homes and objects.
Why it matters for physical AI
It is an openly available pi-family checkpoint aimed at open-world mobile manipulation, and it works with the LeRobot tooling.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download lerobot/pi05_baseUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
pi0, pi0-FAST or pi0.5: which base do you fine-tune first?
LeRobot now ships ports of three Physical Intelligence checkpoints. pi0 uses flow matching, pi0-FAST predicts compressed action tokens, and pi0.5 adds co-training aimed at unfamiliar scenes.
More vision-language-action
Browse allA 3B cross-embodiment robot foundation model from NVIDIA that combines a vision-language backbone with a diffusion-transformer action head and can be post-trained on a new robot with a modest amount of data.
A 7B vision-language-action model on a Llama 2 backbone that maps one camera image and a text instruction to discretized 7-DoF end-effector actions, trained on Open X-Embodiment episodes.