Ant's Ling-3.1-flash: 560B Parameters, 1M Context

Ant Group unveiled Ling-3.1-flash, a 560B-parameter MoE model activating only 25B per token with a 1M-token context window, free for two weeks before open-sourcing.

2026-10-01 ~ 2026-10-01 · 3 related posts

• Ant's Ling-3.1-flash: 560B MoE with 25B active, 1M context, open-source soon — _AndrewZhao · 2026-10-01
• Ling-3.1-flash surfaces: ~560B total params, ~25B active per token, up to 1M context — Muhlwa_Sholanke · 2026-10-01

1 near-duplicate retellings: Elouakili_Flexy