AIMarkTechPostabout 21 hours ago
Zyphra Releases Zamba2-VL Hybrid Vision-Language Models
9 min read
Zyphra released Zamba2-VL, a family of open vision-language models in 1.2B, 2.7B, and 7B sizes. The models use a hybrid Mamba2 state-space and Transformer backbone to cut time-to-first-token by about an order of magnitude while maintaining competitive accuracy.
Level
Hype check
Tap to vote and see what everyone thinks.
