清华大学 TSAIL（thu-ml）
RDT2-VQ
8.29B Commercial use OK 8/8 verified
Facts
- Released
- 2025-09 1 Source
- Parameters
- 8.29 B 1 Source
- Architecture
- Monolithic autoregressive 0 Source
- License
- Apache-2.0（代码与模型卡） 2 Source
- Commercial
- Commercial use OK 0 Source
- Weights
- huggingface.co ↗ 1 Source
- Code
- github.com ↗ 1 Source
- Paper
- arxiv.org ↗ 0 Source
- Input modalities
- rgb · language 0 Source
- Action space
- 24 步 × 20 维相对动作块（双臂末端） 0 Source
- Cross-embodiment
- 10,000+ 小时、100+ 室内场景的 UMI 人类操作数据；双臂 UR5e / 双臂 Franka FR3 零样本 1 Source
- Pretraining data (hours)
- 10000 h 1 Source
- Target forms
- Dual arm 0 Source
Architecture · Qwen2.5-VL-7B-Instruct 改造的自回归 VLA，Residual VQ 动作分词器；另有 flow-matching 版 RDT2-FM；以 UMI 手持夹爪采的人类操作数据预训练，零样本跨本体
Sources · 2 sources
release_date,license,arch_notes,cross_embodiment,pretrain_hours,code_url https://github.com/thu-ml/RDT2 Official page · Fetched 2026-09-05 · No snapshot stored yet README：2025-09 模型、2026-02 论文；Apache-2.0；Qwen2.5-VL-7B-Instruct；Residual VQ；10,000+ hours；Bimanual UR5e / FR3 / UMI gripper
params_b,weights_url,license https://huggingface.co/api/models/robotics-diffusion-transformer/RDT2-VQ Model hub page · Fetched 2026-09-05 · No snapshot stored yet safetensors 8,292,166,656；license: apache-2.0；createdAt 2025-09-22
Tutorials
No tutorial yet. First one planned: running this model on a rented RTX 4090 with a measured latency report.
Record history
2026-09-05
Sources fetched
release_date,license,arch_notes,cross_embodiment,pretrain_hours,code_url · params_b,weights_url,license
Latency & cost
cost = p50 ms ÷ 1000 × rental ÷ 3600 × 1000
| Hardware | p50 ms | p95 ms | Peak VRAM | Cost per 1k inferences ¥ | samples |
|---|---|---|---|---|---|
NVIDIA RTX 4090 ¥1.68/h · 共绩算力 (2026) | — | — | — | — no latency data | No data |
NVIDIA RTX 5090 ¥2.4/h · 润云 2.4 / 共绩 2.5 / 并行智算云 2.98 (2026) | — | — | — | — no latency data | No data |
NVIDIA A100 80GB no rental price | — | — | — | — no latency data | No data |
NVIDIA Jetson AGX Thor no rental price | — | — | — | — no latency data | No data |
NVIDIA H100 80GB no rental price | — | — | — | — no latency data | No data |
No latency measurements for this model yet · Data comes from literature, maintainer runs, or crowd CLI uploads. None exist so far.
Compatibility
Colored only where we hold evidence. An amber dot means the vendor declares this form as a target; that is a claim, not a verified compatibility.
| Unitree G1 | Unitree H1 | 智元 精灵 G1 | 松灵 Piper 机械臂 | SO-101 | Franka FR3 / Panda | Fourier GR-2 | WidowX 250 S | Google Robot（Everyday Robots） | ALOHA 2 / Cobot Magic（双臂） | Galaxea R1 Pro | Franka Emika Panda | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RDT2-VQ |
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 1 / 12 cells with a definite status
Clear direction, grounded judgement.