Model Overview Description: The NVIDIA DeepSeek V3.2 NVFP4 model is a quantized version of DeepSeek AI’s DeepSeek V3.2 model, an autoregressive language model that uses an optimized Transformer architecture. For more information, refer to the DeepSeek V3.2 model card. The NVIDIA DeepSeek V3.2 NVFP4 model was quantized using the TensorRT Model Optimizer. This model is ready for commercial/non commercial use. Third Party Community Consideration This model is not owned or developed by NVIDIA. This model has been developed and built to a third party’s requirements for this application and use case; see link to Non NVIDIA (DeepSeek V3.2) Model Card. License/Terms of Use: MIT Deployment Geography: Global Use Case: Developers looking to take off the shelf, pre quantized models for deployment in AI Agent systems, chatbots, RAG systems, and other AI powered applications. Release Date: Huggingface 01/20/2026 via https://huggingface.co/nvidia/DeepSeek V3.2 NVFP4 Model Architecture: Architecture Type: Transformers Network Architecture: DeepseekV32ForCausalLM This model was developed based on DeepSeek V3.2 Number of model parameters: Undisclosed. Input: Input Type(s): Text Input Format(s): Stri…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy