embedl/Cosmos-Reason2-2B-W4A16-Edge2
Image-Text-to-Text • 2B • Updated • 11.9k • 12
EdgeN
Quantization strategy where most weights are converted to INT4, activations remain in FP16, and sensitive layers are preserved in FP16.
Quantization strategy where most weights are converted to INT4, activations remain in FP16, and sensitive layers are preserved in FP16.