Skip to content
Search models or paste a model link. Press Enter to search.

Cosmos3 Edge

nvidia/Cosmos3-Edge
Left and right arrow keys switch the vendor.
Embedl-optimized
Cosmos3 Edge architecture graph
Cosmos3 Edge architecture graph
  • nvidia/Cosmos3-Edge
  • INT4
  • Orin Nano Super
Labels
  • Image
  • Text
  • VLM
  • Generation
Build
Embedl-optimized
Precision
INT4 weights
Runtime
TensorRT Edge-LLM 0.10.1 with Embedl optimizations
Context length
4,096 tokens
Run Cosmos3 Edge on Orin Nano Super

NVIDIA's Cosmos3 Edge reasoner: the 2.4B text-and-image-in, text-out part of NVIDIA's open world model for on-device physical AI.

Methodology

  • Throughput: one user, batch 1, greedy, a 1,705-token text prompt in, 128 tokens out, with the build's EAGLE3 drafting (top-k 3, 4 steps, verify tree 16), in MAXN_SUPER. End-to-end is the whole request; prompt processing is the 1,705 prompt tokens over the time to first token (651 ms); decode excludes prefill. Text prompts only.
  • Accuracy: greedy, the same INT4 model: MMMU-Pro, AI2D, MMBench and DocVQA 1,500 questions each, RealWorldQA all 765.
  • Memory: peak GPU memory during the throughput run.
  • Size: the runtime container (download and on disk), the model image, and its TensorRT engines.
  • Baseline TensorRT Edge-LLM: the FP16 model on upstream TensorRT Edge-LLM with plain decode, same device and prompt; decode only.

Files

Image Size

Model

docker.io/embedl/model-artifacts:hf.nvidia.cosmos3-edge.int4-eagle3.orin-nano-super.b1ec138700741530

2.46 GiB

Runtime

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

0.91 GiB