Half-billion-parameter vision-language model from Hugging Face that answers questions about images and short video clips.
nvidia/Cosmos-Reason2-2B
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelVision-language2.4B paramsEst. 24 GB GPUEstimated minimum compute for inference: Desktop GPU with about 24 GB of memory. Not a benchmark.NVIDIA Open Model LicenseCustom or unstated terms. The upstream license governs use.GatedGated upstream: accept the owner's terms on Hugging Face to download.
About
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.
Why it matters for physical AI
It gives robots a compact embodied-reasoning and planning VLM, and NVIDIA has tested it on edge hardware like Jetson AGX Thor.
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 nvidia/Cosmos-Reason2-2BUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
Are video world models ready for robot planning?
V-JEPA 2 plans in a learned latent space, while Cosmos generates future video that can stand in for rollouts or synthetic training data.
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.