清华大学 / 字节跳动 Research / 中科院自动化所 等
RoboVLMs（KosMos P.H.）
Commercial use OK 7/8 verified
1 of 8 required fields are unverified. They are shown as badges, not filled with defaults. Sources for verified fields are listed below.
Facts
- Released
- 2024-12 1 Source
- Parameters
- Unverified 0 Source
- Architecture
- VLM + action expert 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
- 末端位姿增量 + 夹爪 0 Source
- Cross-embodiment
- Open X-Embodiment 预训练；CALVIN / SimplerEnv / 真机 0 Source
- Pretraining data (hours)
- Unverified 0 Source
- Target forms
- Single arm 0 Source
Architecture · 把任意 VLM 变成 VLA 的框架；表现最好的是 KosMos 主干 + 策略头；Nature Machine Intelligence 2026
Sources · 2 sources
release_date,license,arch_notes,code_url https://github.com/Robot-VLAs/RoboVLMs Official page · Fetched 2026-09-05 · No snapshot stored yet README：initial release 12/11/24；Apache-2.0 license；KosMos VLM backbone；Nature Machine Intelligence
weights_url,license https://huggingface.co/api/models/robovlms/RoboVLMs Model hub page · Fetched 2026-09-05 · No snapshot stored yet 模型卡 license: apache-2.0；checkpoints kosmos_ph_oxe-pretrain.pt 等
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,code_url · 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RoboVLMs（KosMos P.H.） |
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 2 / 12 cells with a definite status
Clear direction, grounded judgement.