Parameters
10B
Modality
Video
Auxiliary Parameters
4.86B
Architecture
Diffusion Transformer
License
Apache 2.0
Release Date
22 Oct 2024
API Pricing (per 1M)
Self-hosted only
Precision
Workload Memory: 7.72 GB
INT4 · 1024x1024
DiT Backbone Weights: 4.66 GB
VAE Decode Workspace: 0.56 GB
Runtime & Graphs: 2.50 GB
1x NVIDIA L4 24GB
7.7 / 21.6 GB usable
1x RTX 3060 12GB
7.7 / 10.8 GB usable
Apple M4 24GB
7.7 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Mochi 1 Preview is a 10B parameter video DiT developed by Genmo, featuring Asymmetric Diffusion Transformer (AsymmDiT) blocks and 8.4x spatio-temporal VAE compression for motion fluidity.
Attention
Attention Heads
24
Attention Head Dimension
128
Dimensions
Auxiliary Parameters
4.86B
Hidden Dimension Size
3,072
Number of Layers
48