AntLingAGI Open-Sources 560B Parameter Ling-3.1-flash Model

AntLingAGI released Ling-3.1-flash, a 560B parameter open-weights reasoning model with 25B active parameters per token and a 1M token context window, targeting coding, office, and agent tasks. The model supports vLLM and SGLang inference frameworks and uses MXFP4 and block-FP8 quantization to reduce weights from 534GB to 292GB, enabling deployment on 4 Hopper GPUs.