Alibaba DAMO Academy
RynnVLA-001
7.01B Commercial terms unverified 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
- 2025-08 1 Source
- Parameters
- 7.01 B 1 Source
- Architecture
- ViLLA 0 Source
- License
- Apache-2.0 (code and model card); README also states research preview intended for non-commercial use ONLY 2 Source
- Commercial
- Commercial terms unverified 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
- Arm joints/end-effector (LeRobot-format data) 0 Source
- Cross-embodiment
- Egocentric human-video pretraining transferred to robot arms 0 Source
- Pretraining data (hours)
- Unverified 0 Source
- Target forms
- Single arm 0 Source
Architecture · Egocentric video generation model as backbone (Chameleon family); video-generation pretraining first, then trajectory modelling and actions
Sources · 2 sources
release_date,license,arch_notes,code_url https://github.com/alibaba-damo-academy/RynnVLA-001 Official page · Fetched 2026-09-04 · No snapshot stored yet README: released 2025-08-08; Apache 2.0; research preview intended for non-commercial use ONLY
params_b,weights_url,license https://huggingface.co/api/models/Alibaba-DAMO-Academy/RynnVLA-001-7B-Base Model hub page · Fetched 2026-09-04 · No snapshot stored yet safetensors 7,013,158,912；license: apache-2.0；base chameleon
Activity signals
Public counters fetched daily from GitHub, Hugging Face and ModelScope. Numbers only; no judgement. · fetched 2026-10-31
GitHub stars
302
±0 / 30 d
Commits · 90 d
0
last push 282 d ago
HF downloads · 30 d
22
all-time 175 · 9 likes
Weights last modified
2025-09-18
409 d ago
GitHubalibaba-damo-academy/RynnVLA-001 · 19 forks · 12 open issues · no GitHub releaseno push for 281 d
ModelScopeDAMO_Academy/RynnVLA-001-7B-Base · 224 downloads · updated 2025-11-26 · same-name mirror, not the vendor org
Hugging FaceAlibaba-DAMO-Academy/RynnVLA-001-7B-Base
stars · last 30 d
Public benchmark scores
As printed in the source; protocols differ between papers. Full table with notes on the benchmarks page.
| Benchmark | Subset | Score | Source |
|---|---|---|---|
| CALVIN | abc_d | 4.2 avg_len | paper · Table 5, row 'Full Model', Task ABC -> D, Avg. Len. |
| Real-robot evaluation (self-reported) | avg | 90.6 | paper · Table 1, row 'RynnVLA-001 (Ours)', Average (%) |
| Real-robot evaluation (self-reported) | Grab pen and put it into holder | 90 | paper · Table 1, row 'RynnVLA-001 (Ours)', column 'Grab pen and put it into holder' |
| Real-robot evaluation (self-reported) | Instruction-following with Distractors | 91.7 | paper · Table 2, row 'RynnVLA-001 (Ours)', column 'Instruction-following with Distractors' |
| Real-robot evaluation (self-reported) | Multi-Target Manipulation | 86.7 | paper · Table 2, row 'RynnVLA-001 (Ours)', column 'Multi-Target Manipulation' |
| Real-robot evaluation (self-reported) | Pick up and place green blocks | 90 | paper · Table 1, row 'RynnVLA-001 (Ours)', column 'Pick up and place green blocks' |
| Real-robot evaluation (self-reported) | Pick up and place strawberries | 91.7 | paper · Table 1, row 'RynnVLA-001 (Ours)', column 'Pick up and place strawberries' |
| Real-robot evaluation (self-reported) | Single-Target Manipulation | 93.3 | paper · Table 2, row 'RynnVLA-001 (Ours)', column 'Single-Target Manipulation' |
Deployment recipe
No recipe yet. We publish only steps that actually ran on a rented GPU with a measured latency; this model has not been through that yet.
Record history
2026-09-04
Sources fetched
release_date,license,arch_notes,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 · GongJi Compute (2026) | — | — | — | — no latency data | No data |
NVIDIA RTX 5090 ¥2.4/h · Runyun 2.4 / GongJi 2.5 / Paratera Cloud 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 |
NVIDIA A800 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 | AgiBot Genie G1 | AgileX Piper arm | SO-101 | Franka FR3 / Panda | Fourier GR-2 | WidowX 250 S | Google Robot（Everyday Robots） | ALOHA 2 / Cobot Magic (dual-arm) | Galaxea R1 Pro | Franka Emika Panda | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RynnVLA-001 |
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 1 / 12 cells with a definite status
Reproduction records
Did this model run on your robot? Report it with a link (log, video or repo). Records are reviewed by the maintainers; a verified “works” or “works after fine-tuning” upgrades the matrix cell to “community verified” with your link as evidence. Anonymous is fine; nothing but the fields below is stored.
No verified record yet for this model.
Clear direction, grounded judgement.