NVIDIA 发布 Kimi-K2-Thinking NVFP4 量化模型
原标题：nvidia/Kimi-K2-Thinking-NVFP4
AI 摘要
NVIDIA 发布了 Kimi-K2-Thinking-NVFP4，这是 Moonshot AI 的 Kimi-K2-Thinking 模型的量化版本，采用 TensorRT Model Optimizer 进行 NVFP4 量化，支持 vLLM、SGLang 和 TensorRT-LLM 推理，专为 NVIDIA Blackwell 硬件优化。该模型拥有 1T 参数，基于 DeepSeek V3 架构，适用于商业和非商业用途，但 NVIDIA 强调模型并非其开发，并提醒注意潜在偏见和毒性输出。
正文节选
--- pipeline_tag: text-generation base_model: - moonshotai/Kimi-K2-Thinking license: other license_name: modified-mit library_name: Model Optimizer tags: - nvidia - ModelOpt - Kimi-K2 - quantized - FP4 - fp4 --- # Model Overview ## Description: The NVIDIA Kimi-K2-Thinking-NVFP4 model is the quantized version of the Moonshot AI's Kimi-K2-Thinking model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check [here](https://hu