Deepseek Vl2
DeepSeek-VL2 is a chat model developed by DeepSeek, capable of handling text and image inputs, and exceling at tasks such as visual question answering, optical character recognition, and document understanding. It utilizes a Mixture-of-Experts (MoE) architecture, with variants ranging from 1.0B to 4.5B activated parameters, achieving competitive performance with fewer parameters compared to similar models.
Input
Output
Context
4K
Max Output
1K
Parameters
4.5B
Technical Specifications
Model TypeChat
Context Window4,096 tokens
Max Output Tokens512 tokens
Parameters4.5B
Release DateDec 13, 2024
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek Vl2
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.