InternVLA-M1
Robotics modelDual-system spatially guided Vision-Language-Action model built on Qwen2.5-VL-3B-Instruct and a CogACT-style Diffusion Transformer action head with MIT-licensed code, six CC-BY-NC-SA-4.0 (non-commercial) checkpoints, and CUDA, Intel XPU, and CPU runtime support. [1] [2] [3]
Setup & usage →CheckpointsModel hub / homepageGetting started
- For
- Academic and non-commercial robotics researchers exploring Qwen2.5-VL-based VLAs; Teams co-training robot action datasets jointly with multimodal spatial grounding data [1] [3]
- Parameters
- 3,754,622,976 (~3.75B BF16 VLM backbone params in InternRobotics/InternVLA-M1 per HF safetensors metadata [3]
- Embodiments
- Franka Panda (LIBERO Spatial, Object, Goal, Long), WidowX (SimplerEnv Bridge), Google Robot (SimplerEnv Fractal… [1] [4]
- Source rights
- Named licenses are documented by part. Includes noncommercial terms. Review licenses
Source researched · Not tested by us
Sources checked · Research details
Licenses & related hardware
- Ecosystem
- LeRobot
Overview
InternVLA-M1 (InternRobotics/InternVLA-M1, default branch InternVLA-M1; arXiv:2510.13778, ICLR 2026 *ST4VLA*) is a modular dual-system Vision-Language-Action framework from InternRobotics. It pairs a Qwen/Qwen2.5-VL-3B-Instruct vision-language and spatial-grounding head (chat_with_M1 for image Q&A and bounding-box prediction) with a CogACT-inspired Diffusion Transformer (DiT) action head (predict_action using 10-step DDIM sampling and cfg_scale=1.5) trained under joint dual supervision. [1] [3]
Model card summary
- Architecture
Dual-system spatially guided VLA combining a Qwen2.5-VL-3B-Instruct language/spatial-grounding head (Qwen2_5_VLForConditionalGeneration, 36 layers, hidden_size 2048) with a CogACT-inspired Diffusion Transformer (DiT) action head sampled via 10-step DDIM with CFG.
- Parameter count
3,754,622,976 (~3.75B BF16 VLM backbone params in InternRobotics/InternVLA-M1 per HF safetensors metadata; full dual-system .pt action checkpoints are 7.79–8.32 GB)
Exact combined VLM + DiT action-head parameter count is not exposed for the single-file .pt checkpoints.
- Input modalities
- rgblanguage
Multi-view RGB images (e.g., two views in quickstart demo) and English language instructions or spatial grounding prompts.
- Output modalities
- ee-pose-deltagripper-command
Normalized continuous action chunks [B, T, action_dim] for LIBERO and SimplerEnv manipulation tasks (plus text/bounding-box spatial grounding via chat_with_M1).
- Action space
Continuous normalized action chunks [B, T, action_dim] generated by a DiT action head using DDIM sampling (default num_ddim_steps=10, cfg_scale=1.5).
- Trained / supported embodiments
- Franka Panda (LIBERO Spatial, Object, Goal, Long)
- WidowX (SimplerEnv Bridge)
- Google Robot (SimplerEnv Fractal VA/VM)
- Real-robot setups via examples/real_robot
- Training datasets
- System-2 multimodal spatial grounding pretraining dataset (referenced in InternRobotics/InternVLA-M1 model card)
- RT-1 and BridgeData V2 (for InternVLA-M1-Pretrain-RT-1-Bridge)
- Curated OXE and LIBERO multi-task datasets (IPEC-COMMUNITY / GR00T-LeRobot format)
Checkpoints
| Checkpoint | Format | Size | Access | Pinned revision |
|---|---|---|---|---|
| InternRobotics/InternVLA-M1 | safetensors | 6.99 GB | open | ce8a34244d1d |
| InternRobotics/InternVLA-M1-Pretrain-RT-1-Bridge | pytorch | 7.79 GB | open | 6272240f1c14 |
| InternRobotics/InternVLA-M1-LIBERO-Long | pytorch | 8.32 GB | open | 67a325f3f01d |
| InternRobotics/InternVLA-M1-LIBERO-Goal | pytorch | 8.32 GB | open | f02a857ef543 |
| InternRobotics/InternVLA-M1-LIBERO-Spatial | pytorch | 8.32 GB | open | b1bd418dcc3d |
| InternRobotics/InternVLA-M1-LIBERO-Object | pytorch | 8.32 GB | open | 436c7412d3c1 |
All 6 checkpoints are ungated on Hugging Face but licensed CC-BY-NC-SA-4.0 (non-commercial).
Is this for you?
- Use cases
- Dual-supervision spatial Q&A / bounding-box grounding (chat_with_M1) and multi-view robot action prediction (predict_action)
- Benchmark evaluation on LIBERO (Spatial, Object, Goal, Long) and SimplerEnv (WidowX, Google Robot)
- Co-training action datasets with multimodal vision-language supervision
- Running VLA inference on NVIDIA CUDA, Intel GPUs (XPU), or CPU
- Known limitations
- All six published Hugging Face checkpoints are licensed CC-BY-NC-SA-4.0 (non-commercial, share-alike), even though the GitHub codebase is MIT-licensed
- Pretrained RT-1-Bridge and all four LIBERO checkpoints are distributed as single PyTorch .pt files (7.79–8.32 GB) rather than safetensors
- FlashAttention 2 is CUDA-only (Intel XPU and CPU fall back to PyTorch native attention, with minor float32 flow-matching rounding drift noted upstream)
- Minimum inference VRAM, fine-tuning VRAM, and closed-loop control frequency (Hz) are not specified in the README
- Safety and limitations
- All six released checkpoints are licensed CC-BY-NC-SA-4.0, prohibiting commercial use of the published weights despite the MIT-licensed codebase.
- Five of six checkpoints are single-file PyTorch .pt archives requiring trust before deserialization.
- No robot-side safety guardrails or collision interlocks are bundled in the inference server.
Compute & fine-tuning
- Inference compute
- Documented hardware: NVIDIA A100, RTX 4090 (LIBERO eval verified); Intel XPU and CPU also supported
- Precision:
bf16 - Edge / consumer capable: No
Exact minimum VRAM and inference latency_ms are not documented in README.
- Fine-tuning
- Supported: Yes
- Methods: Spatial-prompt and action fine-tuning (~2.5 epochs reported for convergence); Multimodal multi-task co-training (examples/CoTraininig/README.md)
- Recipe: Upstream fine-tuning documentation
- Host computer
Runs on NVIDIA CUDA (LIBERO evaluation verified on A100 and RTX 4090), Intel GPUs (XPU), or CPU with automatic device selection; exact minimum VRAM and latency_ms are not specified.
- Operating system
- Linux
Standard Linux conda, CUDA/XPU, and flash-attn workflow documented.
[1] · Editorial assessment
- Dependencies
- Python 3.10
- PyTorch (CUDA wheels or Intel XPU wheels)
- transformers (4.50.3 recorded in config.json)
- flash-attn (CUDA only; optional on XPU/CPU)
- Qwen/Qwen2.5-VL-3B-Instruct (base VLM)
Setup & usage
Open the upstream getting-started guide [1] · Model card / documentation [1]
- Clone InternRobotics/InternVLA-M1 (default branch InternVLA-M1) and create a Python 3.10 conda environment
- Install requirements.txt, install flash-attn (skip on Intel XPU/CPU), and run pip install -e .
- Download a checkpoint from Hugging Face (e.g., InternRobotics/InternVLA-M1 or a LIBERO/RT-1-Bridge .pt checkpoint)
- Load via InternVLA_M1.from_pretrained(saved_model_path) and call chat_with_M1 or predict_action(batch_images, instructions, cfg_scale=1.5, use_ddim=True, num_ddim_steps=10)
Upstream-reported benchmarks
Upstream-reported only: Open Source Robotics has not run training, inference, or hardware evaluations for these benchmarks.
| Benchmark | Upstream-reported score | Scope & caveats |
|---|---|---|
| LIBERO (Spatial, Objects, Goal, Long) | 95.9% average (Spatial 98.0%, Objects 99.0%, Goal 93.8%, Long 92.6%) | Upstream-reported results in README and examples/LIBERO/README.md (verified on A100 and RTX 4090); not independently reproduced by OSR. |
| SimplerEnv (WidowX, Google Robot VA & VM) | WidowX 71.7%, Google Robot VA 76.0%, Google Robot VM 80.7% | Upstream-reported results in README table (arXiv:2510.13778 / ICLR 2026 ST4VLA); not independently reproduced by OSR. |
Project notes
Six checkpoints, hardware portability, and data loader reuse
Six ungated checkpoints are hosted on Hugging Face: the base InternRobotics/InternVLA-M1 system-2 model (3,754,622,976 BF16 parameters, 6.99 GB safetensors + .bin), InternVLA-M1-Pretrain-RT-1-Bridge (7.79 GB .pt), and four LIBERO task-suite checkpoints (LIBERO-Long, LIBERO-Goal, LIBERO-Spatial, LIBERO-Object, 8.32 GB .pt each). Notably for hardware flexibility, deployment and evaluation scripts automatically select NVIDIA CUDA, Intel GPUs (XPU), or CPU without code changes; Intel XPU skips CUDA-only flash-attn and uses PyTorch's native attention (with minor float32 rounding drift noted upstream). Data loading reuses the GR00T-LeRobot format alongside IPEC-COMMUNITY OXE/LIBERO mixtures, and the repository includes a unified inference server for SimplerEnv and LIBERO plus multimodal co-training recipes. [1] [3] [4]
Upstream-reported benchmarks and undocumented compute limits
In the repository README and examples/LIBERO/README.md, InternVLA-M1 reports a 95.9% average across LIBERO suites (Spatial 98.0%, Objects 99.0%, Goal 93.8%, Long 92.6%) and SimplerEnv scores of 71.7% on WidowX, 76.0% on Google Robot Variant Aggregation, and 80.7% on Google Robot Visual Matching. Separately, upstream reports that the LIBERO evaluation workflow runs on NVIDIA A100 and RTX 4090 GPUs. However, upstream does not specify minimum inference or fine-tuning VRAM, per-step inference latency, or closed-loop control frequency (Hz), and the exact combined VLM + DiT parameter count is not exposed in Hugging Face metadata for the five single-file .pt checkpoints. All benchmark figures are upstream-reported; Open Source Robotics has not run training, fine-tuning, inference, or robot evaluations for this profile. [1] [3] [4]
What we checked
None. Prepared from public upstream sources and Hugging Face API metadata without hands-on training, fine-tuning, or inference.
Not yet established
- Documented closed-loop control frequency (Hz)
Updates
- Upstream last updated
- Oct 9, 2026 [1]
- Latest release
- Nov 24, 2025 [3]
- Profile updated
- Nov 21, 2026
- Sources last checked
- Nov 21, 2026
- Next review
- Feb 19, 2027
- Reviewed revision
- InternRobotics/InternVLA-M1@7f42cf279a3b15d79507b632d37921f5f2f073ba (branch InternVLA-M1); HF InternRobotics/InternVLA-M1@ce8a34244d1da9cf5136743f28f1a619168a5185 · combined hardware and software repository
Separate license matrix
Active dual-system Qwen2.5-VL + DiT VLA framework with MIT-licensed code and six ungated checkpoints; classified as partial openness because all published model weights carry a non-commercial CC-BY-NC-SA-4.0 license.
| Layer | Availability / license |
|---|---|
| Code | available · MIT Verified MIT License (InternVLA Team) in root LICENSE file. [1] [2] |
| Model weights | available · CC-BY-NC-SA-4.0 (non-commercial, share-alike) All 6 InternRobotics/InternVLA-M1* Hugging Face checkpoints declare license: cc-by-nc-sa-4.0. [3] |
| Training datasets | available · Mixed (public IPEC-COMMUNITY OXE/LIBERO datasets have per-dataset licenses; system-2 spatial grounding pretraining dataset is referenced in model card without a standalone license link) Partial availability: public IPEC-COMMUNITY OXE/LIBERO datasets are available, while the system-2 spatial grounding pretraining dataset is not linked as a standalone public dataset. [1] [3] |
| Documentation | available · MIT [1] [2] |
Critical code-vs-weights licensing split
Although the InternRobotics/InternVLA-M1 codebase and documentation are released under the MIT License (verified in the root LICENSE file), all six published Hugging Face model checkpoints declare CC-BY-NC-SA-4.0, which prohibits commercial use and requires share-alike terms on derivative weights. Commercial teams can reuse the MIT training framework on their own data and base models (subject to Qwen/Qwen2.5-VL-3B-Instruct and dataset licenses), but cannot deploy the published InternRobotics/InternVLA-M1* checkpoints commercially. [1] [2] [3]
References
Each source links to the exact revision we read. “Used for” shows where this page relies on it.
- S001 InternRobotics/InternVLA-M1 GitHub repository metadata and README.md
Documents dual-system spatial grounding + DiT action head, CUDA/Intel XPU/CPU support, 6 HF checkpoints, SimplerEnv/LIBERO results, and arXiv:2510.13778 / ICLR 2026 ST4VLA.Revision, date & where cited
InternRobotics (GitHub) · github.com · revision
7f42cf2· GitHub API & README.md at commit 7f42cf279a3b (branch InternVLA-M1, 2026-10-09) · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 7 more - S002 InternRobotics/InternVLA-M1 root LICENSE at pinned commit
MIT License (Copyright InternVLA Team).Revision, date & where cited
InternVLA Team · github.com · revision
7f42cf2· LICENSE at commit 7f42cf279a3b · Accessed Nov 21, 2026
Used for: Separate license matrix - S003 Hugging Face model cards, config.json, and API metadata for 6 InternVLA-M1 checkpoints
All 6 checkpoints are ungated and licensed cc-by-nc-sa-4.0; base InternVLA-M1 is 3,754,622,976 BF16 params (6.99 GB safetensors+bin) on Qwen/Qwen2.5-VL-3B-Instruct; RT-1-Bridge (7.79 GB) and LIBERO (8.32 GB each) are .pt files.Revision, date & where cited
InternRobotics (Hugging Face) · huggingface.co · HF API for InternVLA-M1 (ce8a34244d1d), Pretrain-RT-1-Bridge (6272240f1c14), and 4 LIBERO checkpoints (lastModified Oct–Nov 2025) · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 5 more - S004 InternRobotics/InternVLA-M1 examples/LIBERO/README.md
Reports LIBERO breakdown: Spatial 98.0%, Objects 99.0%, Goal 93.8%, Long 92.6% (95.9% average), verified on NVIDIA A100 and RTX 4090.Revision, date & where cited
InternRobotics (GitHub) · github.com · revision
7f42cf2· examples/LIBERO/README.md at commit 7f42cf279a3b · Accessed Nov 21, 2026
Used for: Model card summary, Is this for you?, Compute & fine-tuning, Upstream-reported benchmarks and 2 more
Correction guidance · Discussion is not enabled · Profile format 0.8.0-draft.1
Change history
2026-11-21 — Initial 0.8.0-draft.1 model profile prepared from InternRobotics/InternVLA-M1@7f42cf279a3b and six HF checkpoints.