Vision Language Models Quantization Collection Vision Language Models (VLMs) quantized by Neural Magic • 20 items • Updated Mar 4 • 6
MambaVision Collection MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. • 13 items • Updated 2 days ago • 34
MoshiVis v0.1 Collection MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 8 items • Updated Mar 21 • 23
view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM Mar 12 • 472