Kimi-K2.6-NVFP4 is an NVIDIA-optimized, quantized version of Moonshot AI's Kimi model. It supports advanced multimodal inputs (text, image, video) and includes specialized tokens and templates for tool calling and structured reasoning. The model is designed for efficient inference on NVIDIA GPUs.
Kimi K sits in PulseGate's Foundation models & chat category. It focuses on deploying high-performance multimodal LLMs with NVIDIA-optimized quantization. Kimi K is an open-source project aimed at AI developers using NVIDIA hardware. The project is open source (Apache-2.0). Kimi K is available on the web and API.
NVIDIA builds and maintains Kimi K, and it first shipped in 2024. The project is developed in the open on GitHub with 3.3k stars and 345 commits in the last 90 days. Among its 3 catalogued features are multimodal processing, tool calling, and custom chat template.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do