Janus 1.3B
DeepSeek's Janus 1.3B is a unified multimodal model that excels at understanding and generating text and images, leveraging a novel autoregressive framework with decoupled visual encoding pathways. Its architecture, based on a single unified transformer, enhances flexibility and alleviates conflicts between visual encoding roles.
Input
Output
Context
4K
Max Output
-
Parameters
1.3B
Technical Specifications
Model TypeChat
Context Window4,096 tokens
Max Output TokensNot available
Parameters1.3B
Release DateOct 18, 2024
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
TextImageAudio
Output Modalities
TextImageAudio
Capabilities
Resources & Links
Estimated GPU Requirements for Janus 1.3B
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.