VTP Large F16d64
Minimax's VTP Large F 16d 64 is a visual tokenizer model that excels at generation tasks, leveraging a combination of contrastive, self-supervised, and reconstruction learning techniques. With its open-source license, this model is notable for its scalability, allowing for better generation performance at the same FLOPs as other models like DiT. The VTP Large F 16d 64 model achieves a zero-shot accuracy of 78.28 and an rFID score of 0.36, demonstrating its capabilities in understanding and reconstruction tasks.
Input
Output
Context
-
Max Output
-
Parameters
731.6M
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Estimated GPU Requirements for VTP Large 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.