Skip to content
Log in

nvidia/Cosmos-Reason1-7B

huggingface_fp16_tensorrt-edgellm
nvidia/Cosmos-Reason1-7B architecture graph
nvidia/Cosmos-Reason1-7B architecture graph
  • huggingface
  • AGX Thor
Labels
  • Text
  • LLM
  • Generation
Build
Embedl-optimized
Precision
W4A16
Runtime
TensorRT Edge-LLM 0.10.1 with Embedl optimizations
Context length
4,096 tokens

NVIDIA's 7B Cosmos-Reason1 vision-language model for physical-world reasoning in robotics and video analytics.

Files

Image Size

Model

docker.io/embedl/model-artifacts:cosmos-reason1-7b.huggingface_int4_embedl_tensorrt-edgellm.a4f9bd9eae5e71ec

 6.47 GiB

Runtime

docker.io/embedl/models:runtimes.tensorrt-edgellm.arm64.2026101815014ee0

 1.01 GiB