π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…
Open-weight model · Robotics
pi05_libero_finetuned_v044
by LeRobot lerobot/pi05_libero_finetuned_v044
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments.
Parameters3.6B
Context—
Weights7.5 GB
Licensegemma
AccessOpen weights
Monthly Downloads24.9k
Runs On
What it takes to serve pi05_libero_finetuned_v044 (3.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 7.2 GB | 8.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 3.6 GB | 4.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 1.8 GB | 2.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Checkpoint trained and evaluated on LIBERO tasks Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full…
Excerpt from the card by LeRobot, licensed gemma.
Identity and Version
- Repository
- lerobot/pi05_libero_finetuned_v044
- Publisher
- LeRobot
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 3.6B parameters
- Languages
- en
- Revision
- 8e174154ef5f6c60a8da12ae99c303d8963138c1
- First published
- 2025-10-01
- Last updated
- 2026-07-29
Files and Weights
9 files, 7.5 GB in total. The weights are 3 files totalling 7.5 GB in safetensors.
Weights3 files · 7.5 GB
Configuration4 files · 10.4 KB
Documentation1 file · 4.4 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 7.5 GB | 877b3ec11305 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 7.7 KB | a002c0df7f79 |
| policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 7.7 KB | a002c0df7f79 |
| config.json | Configuration | 2.2 KB | — |
| policy_postprocessor.json | Configuration | 660 B | — |
| policy_preprocessor.json | Configuration | 1.9 KB | — |
| train_config.json | Configuration | 5.6 KB | — |
| README.md | Documentation | 4.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- gemma
- Access
- Open weights, no gate
- Download size
- 7.5 GB
Download from LeRobot
Released by LeRobot through its official repository on Hugging Face.
Built From
- Described by arXiv:2504.16054
- Trained on (disclosed) HuggingFaceVLA/libero
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 7.5 GB |
| 16-bit | 7.2 GB |
| 8-bit | 3.6 GB |
| 4-bit | 1.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About pi05_libero_finetuned_v044
How much GPU memory does pi05_libero_finetuned_v044 need?
About 8.7 GB at 16-bit and 2.2 GB at 4-bit: the weights (3.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run pi05_libero_finetuned_v044 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use pi05_libero_finetuned_v044 commercially?
Yes, with conditions. pi05_libero_finetuned_v044 is released under Gemma Terms of Use. Gemma models are released under Google's Gemma Terms of Use, which permit commercial use and redistribution subject to the Gemma Prohibited Use Policy, whose restrictions must be passed on to anyone the model is distributed to.
Similar Models
π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…
π₀ is a Vision-Language-Action (VLA) foundation model from Physical Intelligence that jointly reasons over vision, language, and actions to control robots, serving as the base architecture that later enabled π₀.₅’s open-world generalization. Original paper: π0: A Vision-Language-Action Flow Model for General Robot Controlion For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=... - -policy.maxactiontokens=...…
Full fine-tune of lerobot/pi05base on a bimanual actuator-unboxing task, with a speed token in the text prompt: Part of a check whether pi0.5 can be conditioned through text tokens, as a precursor to advantage conditioning (RECAP, π0.6). Data (not on the Hub): 198 teleoperated episodes labelled slow, merged with 437 episodes of the same task demonstrated about 1.75× faster in another session, labelled fast (635 episodes, 371,523 frames; 50 fps, three 224×224 cameras, 14-D state and action). 30 % of training samples get unknown, the null prompt for classifier-free guidance. Training: 4,400 steps (about 3 epochs), batch 256, learning rate 5e-5, 10 % linear warm-up, cosine decay over the last…
Full fine-tune of lerobot/pi05base on a bimanual actuator-unboxing task, with a speed token in the text prompt: Part of a check whether pi0.5 can be conditioned through text tokens, as a precursor to advantage conditioning (RECAP, π0.6). Data (not on the Hub): 198 teleoperated episodes (50 fps, three 224×224 cameras, 14-D state and action) labelled slow, plus two 2× copies of every episode that keep only the even or only the odd frames, labelled fast (594 episodes, 348,616 frames). Slow and fast samples show the same images, so only the token tells them apart. 30 % of training samples get unknown, the null prompt for classifier-free guidance. Training: 4,000 steps (about 3 epochs), batch…
NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) model for generalized humanoid robot skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments. GR00T N1.6 is trained on a diverse mixture of robot data including bimanual, semi-humanoid and an expansive humanoid dataset, consisting of real captured data, synthetic data generated using the components of NVIDIA Isaac GR00T Blueprint. It is adaptable through post-training for specific embodiments, tasks and environments. The neural network architecture of GR00T N1.6 is a combination of vision-language foundation model and diffusion transformer…