ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • NVIDIA
    NVIDIA
    Cosmos Reason-1-7B
    Container
    NVIDIA
    NVIDIA
    Cosmos Reason-1-7B

    This NIM Cosmos Reason-1-7B model which is an open, customizable, 7B-parameter reasoning vision language model (VLM) for physical AI and robotics - enables robots and vision AI agents to reason like humans, using prior knowledge and physics understanding.

  • LayerLabelCreated
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    VLLM_IMAGE_FETCH_TIMEOUT=60
    		09/23/2025 4:02 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    TORCHINDUCTOR_COMPILE_THREADS=32
    		09/23/2025 4:02 PM UTC
    sha256:3ac7f385735fd367b77831eec423352fbb5516650fa026df5c7cf0932a2ff84dRUN
    NIM_MODEL_NAME=nvidia/cosmos-reason1-7b NIM_VERSION=1.4.0 NIM_CONTAINER_NSPECT_ID=NSPECT-9KOC-1EO7 NIM_MODEL_NSPECT_ID=NSPECT-ZEWI-8Y6H NIM_TYPE=vlm NIM_USER_ID=1000 sed -i 's/8192/4096/g' /opt/nim/llm/.venv/lib/python3.12/site-packages/vllm/multimodal/video.py
    		09/23/2025 4:02 PM UTC
    sha256:43243c502b2304ede4d3cfa87d608d44cb74420bf35e1f88e2f5950f62f4a583RUN
    NIM_MODEL_NAME=nvidia/cosmos-reason1-7b NIM_VERSION=1.4.0 NIM_CONTAINER_NSPECT_ID=NSPECT-9KOC-1EO7 NIM_MODEL_NSPECT_ID=NSPECT-ZEWI-8Y6H NIM_TYPE=vlm NIM_USER_ID=1000 sed -i 's/EXECUTE_MODEL_TIMEOUT_S = 40/EXECUTE_MODEL_TIMEOUT_S = 400/g' /opt/nim/llm/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py
    		09/23/2025 4:02 PM UTC
    sha256:c9baa4c39c7dc6657a67c8fb4d0c7d5b0dba8409391c4fa928ffc28fbd67ef74RUN
    NIM_MODEL_NAME=nvidia/cosmos-reason1-7b NIM_VERSION=1.4.0 NIM_CONTAINER_NSPECT_ID=NSPECT-9KOC-1EO7 NIM_MODEL_NSPECT_ID=NSPECT-ZEWI-8Y6H NIM_TYPE=vlm NIM_USER_ID=1000 sed -i 's/config2launcher.get(best_config)/config2launcher.get(best_config, self._precompile_config(best_config).make_launcher())/g' /opt/nim/llm/.venv/lib/python3.12/site-packages/torch/_inductor/runtime/triton_heuristics.py
    		09/23/2025 4:02 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NIM_MEDIA_IO_KWARGS={"video": {"fps": 4.0}}
    		09/23/2025 4:02 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
    		09/23/2025 4:02 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    NVIDIA_PRODUCT_NAME=NVIDIA Inference Microservice VLM NIM
    		09/23/2025 4:02 PM UTC
    sha256:72ca2e669f4cae281ff4bc67607baf8e2470ebb321f069d41069740bd66d3741COPY
    CONTAINER_LICENSE /opt/nim/LICENSE
    		09/23/2025 4:02 PM UTC
    sha256:8534bd6e84ee9b0491c51a2d909f54b72689715e103e7ebaf7bbf983aef32e3dCOPY
    ./notices/* /opt/nim/
    		09/23/2025 4:02 PM UTC
    ...

    NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.