A small reasoning vision-language model fine-tuned from Qwen3-VL-2B for physical common sense, such as judging object interactions, spatial relations, and whether a video is physically plausible.
google/paligemma2-3b-mix-224
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelVision-language3B paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.Gemma termsGatedGated upstream: accept the owner's terms on Hugging Face to download.Single armMobile base
About
Google's 3B vision-language model trained on a mix of tasks, including captioning, visual Q&A, detection and segmentation, at 224px input.
Why it matters for physical AI
A common base for fine-tuning task-specific perception, and a vision backbone used in several VLA robot policies.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
Gated upstream. Accept the owner's terms on Hugging Face and sign in with hf auth login before downloading.
hf download google/paligemma2-3b-mix-224Uses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
More vision-language
Browse allHalf-billion-parameter vision-language model from Hugging Face that answers questions about images and short video clips.
Compact, frequently updated vision-language model with built-in captioning, visual Q&A, object detection and pointing.