AI Agent Hub

Compare LLM Models

Select 2-5 models to compare side by side.

Select models to compare 0 / 5 selected
Top downloads
Select 2-5 models
Attribute
microsoft
Company microsoft
Release Date 2024-06
Parameters (B) 0.8
Architecture DaViT vision encoder with Transformer encoder-decoder (vision-language seq2seq)
Context Window 1024
Input Modalities text, image
Open Source Yes
License mit
Score 0
VRAM (GB) 8
Compute Single NVIDIA GPU with 8GB+ VRAM (FP16 inference)
Pricing (Input) —
Pricing (Output) —