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.
HuggingFaceTB/SmolVLM2-500M-Video-Instruct
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelVision-language507M paramsEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.Apache 2.0Desk deviceMobile base
About
Half-billion-parameter vision-language model from Hugging Face that answers questions about images and short video clips.
Why it matters for physical AI
Small enough to give a device or robot basic scene description and visual Q&A without a cloud call.
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.
hf download HuggingFaceTB/SmolVLM2-500M-Video-InstructUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
What actually runs well on a Raspberry Pi 5?
Our compute tiers are estimates based on parameter counts. Real numbers beat estimates.
More vision-language
Browse allCompact, frequently updated vision-language model with built-in captioning, visual Q&A, object detection and pointing.
Smallest instruction-tuned model in Alibaba's Qwen3-VL line, covering image and video understanding, OCR and grounded object localization.