Tar 1.5B
ByteDance's Tar 1.5B is an open-source model capable of unifying visual understanding and generation via text-aligned representations. It is genuinely best at tasks involving text-aligned representations, as indicated by its model card title.
Input
Output
Context
33K
Max Output
2K
Parameters
2.6B
Technical Specifications
Model TypeChat
Context Window32,768 tokens
Max Output Tokens2,048 tokens
Parameters2.6B
Release DateJul 2, 2025
Training CutoffJan 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImageAudio
Output Modalities
TextImageAudio
Capabilities
Estimated GPU Requirements for Tar 1.5B
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 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.