NVFP4 Quantization

5 posts · 3 sources

CoreweaveBlog30 Jul

CoreWeave Leads on Artificial Analysis for Kimi K2.7 Code Inference

NVIDIABlog10 Jul

AI Model Co-Design: Hardware-Friendly LLM Design

NVIDIABlog4 Jun

NVIDIA Nemotron 3 Ultra Powers Faster, More Efficient Reasoning for Long-Running Agents

CoreweaveBlog20 May

CoreWeave Leads Artificial Analysis Kimi K2.6 Benchmark

BasetenBlog12 Nov

Kimi K2 Thinking at 140+ TPS on NVIDIA Blackwell