embedl/Cosmos-Reason2-2B-W4A16-Edge2
Image-Text-to-Text • 2B • Updated • 133 • 16
Cosmos-Reason2
nvidia/Cosmos-Reason2 multi-modal reasoning models optimized by Embedl.
-
-
embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead
Image-Text-to-Text • 2B • Updated • 70 • 11 -
embedl/Cosmos-Reason2-2B-NVFP4A16
Image-Text-to-Text • 2B • Updated • 1 -
embedl/Cosmos-Reason2-2B-W4A16
Image-Text-to-Text • 2B • Updated • 26 • 13 -
Edge Inference Benchmarks
🚀10On-Device benchmarks across devices and models.
-
embedl/Cosmos-Reason2-32B-W4A16-FlashHead
Image-Text-to-Text • 6B • Updated • 1 -
embedl/Cosmos-Reason2-8B-W4A16-FlashHead
Image-Text-to-Text • 3B • Updated • 1 -
nvidia/Cosmos-Reason2-2B
Image-Text-to-Text • 2B • Updated • 565k • 386 -
nvidia/Cosmos-Reason2-8B
Image-Text-to-Text • 9B • Updated • 67.5k • 256