Gemma 3 QAT
Collection
Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory
โข
8 items
โข
Updated
โข
85
Generate high-quality audio from text using various controls
A text-to-speech model powered by SparkAudio and Mobvoi.
Blazingly Fast and Embarrassingly Simple Song Generation
Gradio demo of CogView4-6B
Wan: Open and Advanced Large-Scale Video Generative Models
Generate images with Switti