Deepseek V2 Lite
DeepSeek V 2 Lite is a chat model developed by DeepSeek, capable of function calling, JSON mode, reasoning, streaming, and text generation. It is particularly suited for applications requiring efficient inference, thanks to its innovative Multi-head Latent Attention (MLA) architecture, which compresses the Key-Value cache into a latent vector.
Input
Output
Context
33K
Max Output
-
Parameters
15.7B
Technical Specifications
Model TypeChat
Context Window32,768 tokens
Max Output TokensNot available
Parameters15.7B
Release DateMay 15, 2024
Training CutoffNov 1, 2023
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek V2 Lite
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.