Allen Institute for AI（Ai2）
MolmoAct
8.12B Commercial use OK 8/8 verified
Facts
- Released
- 2025-08 1 Source
- Parameters
- 8.12 B 1 Source
- Architecture
- Monolithic autoregressive 0 Source
- License
- Apache-2.0（代码与权重） 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 · depth · language 0 Source
- Action space
- 末端位姿增量 + 夹爪 0 Source
- Cross-embodiment
- MolmoAct 自采 1 万 episodes（LeRobot 格式）+ 预训练混合 1 Source
- Pretraining data (hours)
- Unverified 0 Source
- Target forms
- Single arm 0 Source
Architecture · Molmo 系：SigLIP2 视觉 + Qwen2.5-7B 语言 + VQVAE 深度编码，先推理空间轨迹再出动作
Sources · 2 sources
release_date,license,cross_embodiment,code_url https://github.com/allenai/MolmoAct Official page · Fetched 2026-09-04 · No snapshot stored yet README：2025-08-12 模型发布、2025-10-24 代码发布；Apache-2.0；10k robot episodes 自采；Google Robot / Franka
params_b,weights_url,license https://huggingface.co/api/models/allenai/MolmoAct-7B-D-0812 Model hub page · Fetched 2026-09-04 · No snapshot stored yet safetensors 8,119,417,808（F32）；license: apache-2.0；base Qwen/Qwen2.5-7B + siglip2-so400m
Tutorials
No tutorial yet. First one planned: running this model on a rented RTX 4090 with a measured latency report.
Record history
2026-09-04
Sources fetched
release_date,license,cross_embodiment,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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MolmoAct |
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 3 / 12 cells with a definite status
Clear direction, grounded judgement.