Kimi-K3.1-Pro-NVFP4

About

This is NVIDIA's NVFP4 quantized version of Moonshot AI's Kimi-K3.1-Pro, a multimodal Mixture-of-Experts model with 2.8T total parameters, 104B activated parameters and a 1,048,576-token context window. It was quantized with NVIDIA Model Optimizer so developers can deploy a pre-quantized model for agents, chatbots and retrieval systems. The model card notes that NVIDIA did not develop the base model, and use is governed by the NVIDIA Open Model Agreement plus the base model license.