VTP Small F16d64
Developed by Minimax, VTP Small F 16d 64 is an open-source model that excels at generation tasks, particularly when integrated with contrastive, self-supervised, and reconstruction learning. Notably, it features a scalable architecture that allows for better generation performance compared to traditional auto-encoders, even with the same FLOPs in DiT training.
Input
Output
Context
-
Max Output
-
Parameters
167.2M
Technical Specifications
Model TypeEmbedding
Context WindowNot available
Max Output TokensNot available
Parameters167.2M
Release DateDec 16, 2025
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Image
Output Modalities
Embedding
Capabilities
Estimated GPU Requirements for VTP Small F16d64
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.