Spaces:

nvidia
/

README

Running

mingyuliutw commited on Jul 22

Commit

26806d0

verified ·

1 Parent(s): 34cee8f

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -78,7 +78,7 @@ One model replaces a stack of pipelines, serving as a vision-language model, vid
 - **[Cosmos 3 Super](https://huggingface.co/nvidia/Cosmos3-Super)**: The 32B-class omni-model (32B reasoner + 32B generator) for large-scale synthetic data generation (SDG) and research. Runs on NVIDIA Hopper and Blackwell GPUs.
 - **[Cosmos 3 Nano](https://huggingface.co/nvidia/Cosmos3-Nano)**: The 8B-class omni-model (8B reasoner + 8B generator) optimized for efficient inference on workstation-grade compute like the RTX PRO 6000.
-- **[Cosmos 3 Edge](https://huggingface.co/nvidia/Cosmos3-Edge)** *(coming soon)*: The 4B-class omni-model (2B reasoner + 2B generator) optimized for real-time robotic policy and visual reasoning on the edge.
 Supporting the models across the platform:

 - **[Cosmos 3 Super](https://huggingface.co/nvidia/Cosmos3-Super)**: The 32B-class omni-model (32B reasoner + 32B generator) for large-scale synthetic data generation (SDG) and research. Runs on NVIDIA Hopper and Blackwell GPUs.
 - **[Cosmos 3 Nano](https://huggingface.co/nvidia/Cosmos3-Nano)**: The 8B-class omni-model (8B reasoner + 8B generator) optimized for efficient inference on workstation-grade compute like the RTX PRO 6000.
+- **[Cosmos 3 Edge](https://huggingface.co/nvidia/Cosmos3-Edge)**: The 4B-class omni-model (2B reasoner + 2B generator) optimized for real-time robotic policy and visual reasoning on the edge.
 Supporting the models across the platform: