OpenVLA provides an open-source vision-language-action model for robotic manipulation tasks.
Open source
24 alternativesSmolVLA
Use SmolVLA, a vision-language-action model trained on data from the LeRobot community, for robotics research.
About SmolVLA
SmolVLA is a 450M-parameter vision-language-action model for robotics that takes raw visual observations and natural language instructions and outputs robot actions. It was pretrained on public, community-shared datasets under the lerobot tag and includes recipes to finetune the pretrained model or train from scratch.
It runs on CPU and trains on a single consumer GPU or MacBook, with deployment on hardware such as SO-100, SO-101, and LeKiwi. It uses an asynchronous inference stack that separates action execution from perception, which is reported to improve response speed and task throughput.
Key features
- Converts raw visual observations and language instructions into robot actions
- Runs on CPU and trains on single consumer GPU or MacBook
- Pretrained on public community-shared datasets under lerobot tag
- Includes recipes to finetune pretrained model or train from scratch
- Uses asynchronous inference to separate action execution from perception
- Deploys on SO-100, SO-101, and LeKiwi robot hardware
Best for: Robotics researchers working with public manipulation datasets and low-cost robot hardware.
Good for
- 450M size runs on CPU and trains on a single consumer GPU or MacBook
- Pretrained only on compatibly licensed public community-shared datasets
- Reported simulation and real-world results on LIBERO, Meta-World, SO100, and SO101
SmolVLA at a glance
- Website
- huggingface.co/blog/smolvla
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
SmolVLA alternatives
Tools and sites you could use instead, ranked by how closely they match.
The Stanford AI Index gathers data about artificial intelligence for researchers, policymakers, journalists, and the public.
The Stanford Alpaca project presents a replicable instruction-following language model and its research materials.
Google Research introduced Imagen as a text-to-image diffusion model in this research paper.
This research paper presents Word-As-Image, a method for incorporating semantic meaning into typography.
CLIPasso explores semantically aware object sketching as a research project.
Popular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comStable Diffusionhuggingface.co/CompVis/stable-diffusion-v1-4Bloomhuggingface.co/docs/transformers/model_doc/bloom
SmolVLA FAQ
What hardware does SmolVLA support for running and training?
It runs on CPU and trains on a single consumer GPU or MacBook, with deployment on SO-100, SO-101, and LeKiwi hardware.
What data was SmolVLA trained on?
Public community-shared robotics datasets under the lerobot tag, using fewer than 30,000 training episodes.
How can developers adapt SmolVLA to their own tasks?
Use the released recipes to finetune the pretrained model for a specific task or train from scratch after pretraining on general manipulation data.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.