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
Thinking Machines Lab
Inkling
Container
Thinking Machines Lab
Inkling

This NIM container houses Inkling model, which is a 66-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) feed-forward backbone, featuring 975B total parameters and 41B active parameters

NVIDIA NIM
LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_MODEL_PATH=ngc://nim/thinkingmachines/inkling:nvfp4-1.3
07/15/2026 11:16 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
1000
07/15/2026 11:16 PM UTC
sha256:fe9f4facc62c66a8c6da02310df0da505ecf3315423faf96a8fdd3d6aa011df6RUN
chown nim:0 /opt/nim/etc/default/model_manifest.yaml
07/15/2026 11:16 PM UTC
sha256:537cb9104718c26024df8ad11cc0282d18d5f55c0ee4d2571cd031a18686eb08COPY
model_manifest.yaml /opt/nim/etc/default/model_manifest.yaml
07/15/2026 11:16 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
0
07/15/2026 11:16 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4CMD
/opt/nim/start_server.sh
07/15/2026 9:42 PM UTC
sha256:c0a2eff17530f116b730b0e68341637b8a101826a1d304b3ff357534633a84a2COPY
--chown=nim:nim NOTICE /opt/nim/NOTICE
07/15/2026 9:42 PM UTC
sha256:b00306c65827af4f4c8ccfac83393fa48a36f105dd0f7328d3efa92c70972af5COPY
--chown=nim:nim MODEL_LICENSE /opt/nim/MODEL_LICENSE
07/15/2026 9:42 PM UTC
sha256:0d1ff3cc5757f7880f28614c482b13011271efbd7cf1cf1d0fda041beb3067f6COPY
--chown=nim:nim model_manifest.yaml /opt/nim/etc/default/model_manifest.yaml
07/15/2026 9:42 PM UTC
sha256:411c6028bda850f4ac3ecbde2d2d977a8de0b641486224738d1f2acc01f5e7dbCOPY
--chown=nim:nim VERSION /opt/nim/VERSION
07/15/2026 9:42 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.