SGLang announces Day-0 support for Ling-3.1-flash from AntLingAGI, a 560B-parameter MoE hybrid reasoning model with 25B active parameters and 1M context.
MXFP4 and block-FP8 quantization reduce the weights from about 534GB to about 292GB, which the post says fits on 4 Hopper GPUs. The post also cites strong results on GDPVal-AA, FrontierSWE, and Terminal-Bench 4.0 for agent, office, and coding tasks.
SGLang has Day-0 support for Ling-3.1-flash from @AntLingAGI!
A 560B MoE hybrid reasoning model, 25B active, 1M context, built for real work: it turns a rough brief into a page, mobile UI, or interactive prototype.
✅ MXFP4 + block-FP8 quantization cuts weights from ~534GB to ~292GB, fitting on 4 Hopper GPUs
✅ Strong on real-world agent, office, and coding tasks, including GDPVal-AA, FrontierSWE, and Terminal-Bench 4.0.
Get started with SGLang:
Ling-3.1-flash is now open source: ~560B total parameters, ~25B active per token and up to 1M context. Built for real work, it can turn a rough brief into a page, mobile UI or interactive prototype teams can review and refine. See the demo.
Source: SGLang · x.comPublished
