π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and…
Open-weight model · Robotics
pi05-real-workbench-preset-3view-object-identification-60k
by Jaehyun Kang jaehyunkang/pi05-real-workbench-preset-3view-object-identification-60k
Final checkpoint after 60,000 optimization steps. This is a trained policy, not an evaluation result. Policy weights, policy configuration, preprocessing/postprocessing and normalization states are at the repository root.
Parameters4.1B
Context—
Weights24.5 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve pi05-real-workbench-preset-3view-object-identification-60k (4.1B 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 | 8.3 GB | 9.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.1 GB | 5.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.1 GB | 2.5 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
Final checkpoint after 60,000 optimization steps. This is a trained policy, not an evaluation result. Policy weights, policy configuration, preprocessing/postprocessing and normalization states are at the repository root. Training resume files are in trainingstate/. Host-specific paths were removed from JSON metadata; supply local dataset/output paths when resuming. The tokenizer reference points to google/paligemma-3b-pt-224 (training revision 35e4f46485b4d07967e7e9935bc3786aad50687c). For subtask models, supply the corresponding per-frame subtask as the policy task text. For 3-view models also supply the dataset-defined keyframe image. No real-robot evaluation metrics are claimed here.…
Excerpt from the card by Jaehyun Kang.
Identity and Version
- Repository
- jaehyunkang/pi05-real-workbench-preset-3view-object-identification-60k
- Publisher
- Jaehyun Kang
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 4.1B parameters
- Languages
- Not stated by the source
- Revision
- 74222328f425fca0d2ccfbab9a3d43978b269ce9
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
15 files, 24.5 GB in total. The weights are 5 files totalling 24.5 GB in safetensors.
Weights5 files · 24.5 GB
Configuration8 files · 24.4 KB
Documentation1 file · 1.7 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 9.4 GB | d198c6afaabb |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 5.4 KB | b3d0693e3df5 |
| policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 5.4 KB | 8c3689d3fe12 |
| training_state/optimizer_state.safetensors | Weights | 15.1 GB | cdb55c0ca7db |
| training_state/rng_state.safetensors | Weights | 15.7 KB | 81e031e3368d |
| artifact_manifest.json | Configuration | 2.2 KB | — |
| config.json | Configuration | 3.0 KB | — |
| policy_postprocessor.json | Configuration | 779 B | — |
| policy_preprocessor.json | Configuration | 2.1 KB | — |
| train_config.json | Configuration | 6.9 KB | — |
| training_state/optimizer_param_groups.json | Configuration | 9.2 KB | — |
| training_state/scheduler_state.json | Configuration | 210 B | — |
| training_state/training_step.json | Configuration | 19 B | — |
| README.md | Documentation | 1.7 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 24.5 GB
Download from Jaehyun Kang
Released by Jaehyun Kang through its official repository on Hugging Face.
Built From
- Derived from lerobot/pi05_base
- Trained on (disclosed) Myungkyu/real_workbench-preset-gemini
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 24.5 GB |
| 16-bit | 8.3 GB |
| 8-bit | 4.1 GB |
| 4-bit | 2.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About pi05-real-workbench-preset-3view-object-identification-60k
How much GPU memory does pi05-real-workbench-preset-3view-object-identification-60k need?
About 9.9 GB at 16-bit and 2.5 GB at 4-bit: the weights (4.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run pi05-real-workbench-preset-3view-object-identification-60k 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.
Similar Models
Final checkpoint after 60,000 optimization steps. This is a trained policy, not an evaluation result. Policy weights, policy configuration, preprocessing/postprocessing and normalization states are at the repository root. Training resume files are in trainingstate/. Host-specific paths were removed from JSON metadata; supply local dataset/output paths when resuming. The tokenizer reference points to google/paligemma-3b-pt-224 (training revision 35e4f46485b4d07967e7e9935bc3786aad50687c). For subtask models, supply the corresponding per-frame subtask as the policy task text. For 3-view models also supply the dataset-defined keyframe image. No real-robot evaluation metrics are claimed here.…
π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and…
Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales…
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…
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…