Wall-X
Robotics modelVLA training/inference source for WALL-series robot policies, with separate published checkpoint listings and CUDA operator builds. [1] [3]
Setup & usage →CheckpointsModel hub / homepageGetting started
- For
- Robot-learning researchers working with CUDA and LeRobot data [1]
- Parameters
- 4,162,224,832 (~4.16B [31]
- Embodiments
- Franka (RoboChallenge / DROID), UR5 (Berkeley Autolab / RoboChallenge), ALOHA (RoboChallenge), … [31]
- Source rights
- Some licenses are unresolved. Review licenses
Source researched · Not tested by us
Sources checked · Research details
Licenses & related hardware
- Ecosystem
- LeRobot
- License
- Apache-2.0 code; checkpoint rights separate · license not fully assessed for model weights · Details by part
Overview
Wall-X (x-square-robot/wall-x) provides the training, fine-tuning, and serving codebase for the WALL-series Vision-Language-Action (VLA) models, paired with the public x-square-robot/wall-oss-0.5 checkpoint on Hugging Face. At pinned Hugging Face revision b7dc23a82dbf70a65859c9fdd596703234597028, wall-oss-0.5 contains 4,162,224,832 parameters (~4.16B: 4,158,769,152 BF16 + 3,455,680 F32) in an 8.33 GB ungated model.safetensors file. It builds on a 3B Qwen2.5-VL backbone (Qwen2_5_VLForConditionalGeneration, 36 layers, hidden_size: 2048) augmented with action-generation modules (action_hidden_size: 1024, state_hidden_size: 2048) trained via gradient-bridged co-training across discrete action prediction, multimodal prediction, and continuous flow matching. [1] [3] [30] [31]
Model card summary
- Architecture
Qwen2.5-VL 3B vision-language backbone (Qwen2_5_VLForConditionalGeneration, 36 layers, hidden_size 2048) augmented with dedicated action-generation modules (action_hidden_size 1024, state_hidden_size 2048) trained with gradient-bridged co-training across discrete action prediction, multimodal prediction, and continuous flow matching.
- Base model
Qwen2.5-VL (3B VLM backbone; Qwen2_5_VLForConditionalGeneration)
- Parameter count
4,162,224,832 (~4.16B; 4,158,769,152 BF16 + 3,455,680 F32 per wall-oss-0.5 safetensors metadata)
- Input modalities
- rgbproprioceptionlanguage
Multi-view RGB camera streams (e.g., face_view and right_wrist_view at 448px in config.yml), robot proprioceptive state (512 bins / string representation), and language instructions.
- Output modalities
- ee-pose-deltagripper-command
Default wall-oss-0.5 config.yml defines 26-D relative dual-arm EE Cartesian position + 6D rotation + grippers plus decomposed base velocity, height, and head actions; configurable via embodiment norm_key.
- Action space
Continuous flow-matching and autoregressive discrete action chunks (action_horizon_flow: 32, action_horizon_ar: 32, state_bins: 512); default wall-oss-0.5 config.yml specifies 26-D relative dual-arm EE pose, grippers, velocity, height, and head actions with per-embodiment norm_key normalization.
- Trained / supported embodiments
- Franka (RoboChallenge / DROID)
- UR5 (Berkeley Autolab / RoboChallenge)
- ALOHA (RoboChallenge)
- ARX5 (RoboChallenge)
- 20+ pretrained robot embodiments via norm_key (BridgeData v2, RH20T, AgiBot World Alpha, DobbE, UMI-biarm, Galaxea LeRobot v2.1, RoboCoin)
- Training datasets
- Multi-embodiment mixture (>1M trajectories/epoch across 20+ embodiments including DROID, BridgeData v2, RH20T, AgiBot World Alpha, Fractal, FurnitureBench, BC-Z, RoboChallenge, RoboCoin) plus grounded multimodal corpus and proprietary/internal configurations (ex_normal, x2_normal)
Checkpoints
| Checkpoint | Format | Size | Access | Pinned revision |
|---|---|---|---|---|
| x-square-robot/wall-oss-0.5 | safetensors | 8.33 GB | open | b7dc23a82dbf |
Ungated 8.33 GB model.safetensors verified via Hugging Face API at revision b7dc23a82dbf70a65859c9fdd596703234597028; no license field is declared in the model card metadata.
Is this for you?
- Use cases
- Zero-shot and fine-tuned multi-embodiment manipulation policy evaluation
- VLA fine-tuning on LeRobot-formatted robot demonstration datasets
- Known limitations
- WALL-OSS0.5 card and repository Python environment instructions differ.
- Selected checkpoint is public/ungated in metadata, but no checkpoint license declaration was identified in card/metadata; code Apache2 does not settle weight rights.
- No CUDA build, checkpoint payload, inference, closed-loop control or data rights validated.
Editorial scope assessment from the cited implementation/documentation; no execution or compatibility test.
- Safety and limitations
- WALL-OSS-0.5 model card (Python 3.12) and wall-x repository README (Python 3.10) specify different Python environment routes that must be reconciled before installation.
- The wall-oss-0.5 checkpoint is public/ungated, but no weight license declaration was identified in card/metadata; repository Apache-2.0 does not automatically settle weight or training-data rights.
- Pretraining mixture includes proprietary/internal configurations (ex_normal, x2_normal) alongside public benchmarks.
- No CUDA build, weight execution, inference, or physical closed-loop robot control was tested by Open Source Robotics.
Compute & fine-tuning
- Inference compute
- Documented hardware: NVIDIA CUDA GPU (flash-attn 2.8.3 and compiled CUDA operators required)
- Precision:
bf16 - Edge / consumer capable: No
8.33 GB BF16/F32 safetensors checkpoint with FlashAttention-2 and custom CUDA operators; exact minimum VRAM and latency_ms are not reported.
- Fine-tuning
- Supported: Yes
- Methods: Full fine-tuning via Wall-X repository with LeRobot datasets
- Recipe: Upstream fine-tuning documentation
- Host computer
CUDA-capable NVIDIA GPU required for custom CUDA operators and flash-attn 2.8.3; exact minimum VRAM is not reported in upstream documentation.
- Operating system
- Linux
Inferred from CUDA operator compilation and flash-attn 2.8.3 build instructions.
- Dependencies
- Repository route uses Python3.10 while selected WALL-OSS0.5 model card uses Python3.12
- Requirements, flash-attn2.8.3, DMuon and separately installed LeRobot are documented
- CUDA operator compilation during editable install requires a matching PyTorch/CUDA build environment
Setup & usage
Open the upstream getting-started guide [1]
- Select WALL-OSS0.5 or another named checkpoint and its matching norm_key/action setup; reconcile model-card and code-repository environment instructions before attempting installation.
- Preserve exact source/dependency/model versions and evaluate the selected workflow before connecting physical hardware or reusing data.
Editorial scope assessment from the cited implementation/documentation; no execution or compatibility test.
Upstream-reported benchmarks
Upstream-reported only: Open Source Robotics has not run training, inference, or hardware evaluations for these benchmarks.
| Benchmark | Upstream-reported score | Scope & caveats |
|---|---|---|
| Wall-OSS-0.5 zero-shot real-robot suite (17 tasks, incl. held-out deformable manipulation) | Upstream model card claims non-trivial zero-shot completion directly from the pretrained checkpoint | Upstream-reported claim on the Hugging Face model card; not independently executed or verified by OSR. |
| Wall-OSS-0.5 fine-tuned real-robot suite (15 tasks) | 60.5% average task progress (upstream card reports +17.5% over pi_0.5) | Upstream-reported figure on the Hugging Face model card; not independently executed or verified by OSR. |
Project notes
Action space, embodiments, and environment caveats
In config.yml, wall-oss-0.5 configures both continuous flow-matching and autoregressive action horizons (action_horizon_flow: 32, action_horizon_ar: 32, state_bins: 512) with a 26-D default dof_config covering dual-arm relative Cartesian end-effector position, 6D relative rotation, grippers, decomposed base velocity, height, and head actions. Inputs combine multi-view RGB images (448 px in config.yml), proprioceptive state, and language instructions. The model card lists more than 20 supported robot embodiments mapped via norm_key settings—spanning Franka, UR5, ALOHA, and ARX5 as well as benchmarks such as DROID, BridgeData v2, RH20T, and AgiBot World Alpha—so selecting the matching norm_key and state/action dimensions is essential. [1] [30] [31]
Two installation details require reconciliation before setup: the pinned wall-x README documents a Python 3.10 environment, whereas the wall-oss-0.5 model card documents Python 3.12. The README advertises an Ubuntu 22.04 and CUDA 12.x environment and requires a CUDA-capable NVIDIA GPU (a documented upstream environment rather than an independently verified compatibility range), alongside flash-attn 2.8.3, DMuon (for default training configs), a separate --no-deps LeRobot install, and --no-build-isolation editable installation to compile included CUDA operators against the active PyTorch/CUDA stack. Minimum inference VRAM and control frequency are not stated as single scalars in the upstream docs. [1] [30] [31]
As documented upstream starting points (not executed in this review), basic action inference is invoked with python scripts/fake_inference.py --checkpoint-path <path/to/checkpoint>. For fine-tuning on LeRobot-formatted datasets, the README directs users to workspace/README.md and the template at workspace/example/lerobot/qwen2_5_lerobot_template.yml before running python -m wall_x.trainer.fsdp_trainer.train_fsdp --config <path/to/config.yml>. [1]
Upstream-reported benchmarks and unverified runtime
The wall-oss-0.5 model card reports non-trivial zero-shot completion on a 17-task real-robot suite (including held-out deformable manipulation) and 60.5% average task progress after fine-tuning on 15 real-robot tasks (+17.5% over π0.5). All benchmark results are strictly upstream-reported; Open Source Robotics has not compiled CUDA operators, downloaded or executed checkpoints, run training or inference, or evaluated physical robot behavior. [1] [31]
What we checked
Source research only. Selected implementation/model text, repository tree and license declarations were inspected. No upstream compilation, dependency installation, simulator, network/USB/device integration, data collection, benchmark or physical robot test was performed. Source files are linked rather than redistributed; external services and paid products are not endorsed.
Not yet established
- Documented closed-loop control frequency (Hz)
Updates
- Upstream last updated
- Sep 18, 2026 [32]
- Latest release
- Not established
- Profile updated
- Nov 21, 2026
- Sources last checked
- Nov 21, 2026
- Next review
- Feb 19, 2027
- Reviewed revision
- GitHub x-square-robot/wall-x@ce2a1ae31d9ee1028b97ca40e3f66034cf8c0e5f; HF x-square-robot/wall-oss-0.5@b7dc23a82dbf70a65859c9fdd596703234597028 · combined hardware and software repository
Separate license matrix
Distinct robot-facing model contribution with actual implementation/model content and a bounded documented next step. Review covers source artifacts, not operational performance or a complete tested deployment.
| Layer | Availability / license |
|---|---|
| Code | available · Apache-2.0 code; checkpoint rights separate Declaration for the scoped source implementation/documentation; dependencies, external services, model/data assets and inherited file-specific terms require separate checks. No blanket redistribution or operational clearance. [1] [2] [3] |
| Model weights | available · License not fully assessed Ungated 8.33 GB safetensors checkpoint (x-square-robot/wall-oss-0.5) verified at HF revision b7dc23a82dbf70a65859c9fdd596703234597028; cardData has no license declaration, so weight terms remain unverified and separate from repository Apache-2.0. [30] [31] |
| Training datasets | unavailable · License not fully assessed Pretraining combines 20+ open-source robotics benchmarks (individual upstream licenses) with proprietary/internal robot data (ex_normal, x2_normal) not redistributed as a unified open dataset. [31] |
| Documentation | available · Apache-2.0 code; checkpoint rights separate Declaration for the scoped source implementation/documentation; dependencies, external services, model/data assets and inherited file-specific terms require separate checks. No blanket redistribution or operational clearance. [1] [2] [3] |
Separate code, checkpoint, and dataset rights
The x-square-robot/wall-x repository carries an Apache-2.0 license (GitHub last pushed 2026-09-18). However, the x-square-robot/wall-oss-0.5 checkpoint card and Hugging Face API metadata declare no weight license (cardData: None), and the pretraining corpus mixes 20+ open-source benchmarks with proprietary/internal robot configurations (ex_normal, x2_normal). Code Apache-2.0 does not automatically settle weight or training-data reuse rights. [2] [30] [31] [32]
References
Each source links to the exact revision we read. “Used for” shows where this page relies on it.
- S001 Project README
Revision, date & where cited
x-square-robot/wall-x contributors · github.com · revision
ce2a1ae· Project README at · Accessed Nov 1, 2026
Used for: Overview, Model card summary, Is this for you?, Compute & fine-tuning and 4 more - S002 License declaration
Revision, date & where cited
x-square-robot/wall-x contributors · github.com · revision
ce2a1ae· License declaration at · Accessed Nov 1, 2026
Used for: Is this for you?, Compute & fine-tuning, Setup & usage, Separate license matrix - S003 Selected implementation excerpt
Revision, date & where cited
x-square-robot/wall-x contributors · github.com · revision
ce2a1ae· Selected implementation excerpt at · Accessed Nov 1, 2026
Used for: Overview, Is this for you?, Compute & fine-tuning, Setup & usage and 1 more - S004 Repository artifact tree
Revision, date & where cited
x-square-robot/wall-x contributors · github.com · revision
ce2a1ae· Repository artifact tree at · Accessed Nov 1, 2026
Used for: Is this for you?, Compute & fine-tuning, Setup & usage - S030 Published checkpoint card and metadata
Revision, date & where cited
x-square-robot/wall-x contributors · huggingface.co · Published checkpoint card and metadata at · Accessed Nov 1, 2026
Used for: Overview, Checkpoints, Is this for you?, Compute & fine-tuning and 3 more - S031 Hugging Face API metadata, config.json, config.yml, and README for x-square-robot/wall-oss-0.5
4,162,224,832 params (4,158,769,152 BF16 + 3,455,680 F32), 8.33 GB model.safetensors, ungated, Qwen2_5_VLForConditionalGeneration backbone with action_hidden_size 1024, action_horizon_flow 32, 26-D default dof_config, 20+ robot embodiments, no license field in card metadata.Revision, date & where cited
X-Square Robot (Hugging Face) · huggingface.co · HF API, config.json, config.yml, README.md at revision · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 5 more - S032 GitHub API repository metadata for x-square-robot/wall-x
pushed_at 2026-09-18T06:48:24Z, SPDX license Apache-2.0, default branch main.Revision, date & where cited
X-Square Robot (GitHub) · github.com · GitHub REST API /repos/x-square-robot/wall-x · Accessed Nov 21, 2026
Used for: What we checked, Separate license matrix
Correction guidance · Discussion is not enabled · Profile format 0.8.0-draft.1
Change history
2026-11-21 — Migrated from 0.7.0-draft.5 project to 0.8.0-draft.1 model; added verified HF wall-oss-0.5 parameter count (4.16B), 8.33 GB safetensors checkpoint, action space, and upstream-reported benchmarks.