How big is Ling-3.1-flash?

560 billion total parameters with 25 billion active per token, according to the model card.

How do I run Ling-3.1-flash?

The model card recommends SGLang, with a day-zero container and a server recipe for 8 H200 GPUs or 4 GB300 GPUs. A vLLM branch is also supported.

TechAILatest.newsTrackers

Large language model (open weights)

Ling-3.1-flash

Ling-3.1-flash is an open-weight hybrid reasoning model from Ant Group's inclusionAI team, released under the MIT licence in October 2026. It is a hybrid linear-attention mixture-of-experts model with 560 billion total and 25 billion active parameters and a 1M-token context, aimed at agents, coding and office tasks. An updated checkpoint, Ling-3.1-flash-1019, followed on 27 October 2026.

Last reviewed 28 Oct 2026 · by Ant Group

Facts at a glance

Developer	Ant Group (inclusionAI)
Latest checkpoint	Ling-3.1-flash-1019, published on Hugging Face 27 October 2026 source
Parameters	560B total, 25B active (512 routed experts, 8 active, 1 shared) source
Architecture	Hybrid-linear MoE: 63 KDA and 9 gated MLA layers (7:1) source
Context window	1M tokens source
Artificial Analysis Intelligence Index	44 (v4.3.2) for the 1019 checkpoint, as reported by inclusionAI source
License	MIT

Questions people ask

How big is Ling-3.1-flash?: 560 billion total parameters with 25 billion active per token, according to the model card.
How do I run Ling-3.1-flash?: The model card recommends SGLang, with a day-zero container and a server recipe for 8 H200 GPUs or 4 GB300 GPUs. A vLLM branch is also supported.