As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/xiaomi-robotics-0/

# Xiaomi-Robotics-0 (4.7B VLA)

Xiaomi, Xiaomi-Robotics family. Status: legacy. Type: robotics model. Released: 2026-02-12.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `XiaomiRobotics/Xiaomi-Robotics-0-Pretrain` |  | https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-0-Pretrain |
| Project page |  |  | https://xiaomi-robotics-0.github.io |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: image, text
- Output: action
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer robotics models in the registry since its release: 17. The 5 newest:
  - Praxis-1 (2026-09-30) https://postcutoff.com/m/praxis-1/
  - Helix 2.5 (2026-09-17) https://postcutoff.com/m/figure-helix-2-5/
  - UnifoLM-WLA-1.0 (2026-09-10) https://postcutoff.com/m/unifolm-wla-1-0/
  - Skild S1 (Skild Brain) (2026-08-25) https://postcutoff.com/m/skild-s1/
  - Generalist GEN-1.5 (2026-08-19) https://postcutoff.com/m/generalist-gen-1-5/
- After it from Xiaomi: Xiaomi-Robotics-1 (XR-1, 5B) (2026-07-16) https://postcutoff.com/m/xiaomi-robotics-1/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- Real-time asynchronous execution on a consumer GPU: Post-trained for asynchronous execution with aligned timesteps between consecutive action chunks, so rollouts stay smooth despite inference latency; runs on a consumer-grade GPU (per paper). Source: https://arxiv.org/abs/2602.12684
- Strong open sim-benchmark results: LIBERO 98.7% avg; SimplerEnv Visual Matching 85.5%, Visual Aggregation 74.7%, WidowX 79.2%; CALVIN avg length 4.75 (ABC-D) / 4.80 (ABCD-D) (authors). Source: https://xiaomi-robotics-0.github.io

## Notes

4.7B parameters, Qwen3-VL-4B-Instruct backbone; pretrained on cross-embodiment robot trajectories plus vision-language data. Real-robot evals: Lego disassembly and towel folding (bimanual). Checkpoints: -Pretrain, -LIBERO, -Calvin-ABC_D, -Calvin-ABCD_D, -SimplerEnv-WidowX, -SimplerEnv-Google-Robot (HF, 2026-02-10). Paper arXiv 2602.12684 (2026-02-13). Superseded by xiaomi-robotics-1 (July 2026).

Xiaomi's first open VLA. Use [xiaomi-robotics-1](xiaomi-robotics-1.md) for new work.

Sources: [project page](https://xiaomi-robotics-0.github.io), [arXiv 2602.12684](https://arxiv.org/abs/2602.12684), [HF](https://huggingface.co/XiaomiRobotics).

Model page: https://postcutoff.com/m/xiaomi-robotics-0/