SigLino: Vision Foundation Models (SigLIP2 + DINOv3) Collection Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). Stems from the CVPR 2026 AMoE paper. • 5 items • Updated about 13 hours ago • 3
Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated 2 days ago • 51
LTX-2.3 Collection LTX-2.3 base models, quantized models and accompanying LoRAs and IC-LoRAs • 6 items • Updated 2 days ago • 25