Filters
- InclusionAI releases Ling-3.0-flash-Sante, a healthcare MoE with 124B total and 5.1B active parameters
InclusionAI published Ling-3.0-flash-Sante on Hugging Face, a healthcare-specialized model built on Ling-3.0-flash (named from French santé, “health”). The model card says it has 124B total parameters and 5.1B active parameters per token, hybrid-linear MoE with training extended to 256K tokens, thinking mode on by default, and tool calling via compatible serving frameworks. Weights are on Hugging Face and ModelScope; the card warns it is a research model, not a medical device. DailyCited is adding the Official listing today after confirming the Hugging Face weights page.
- inclusionAI open-sources Ling-3.1-flash under MIT, a 560B-total, 25B-active hybrid reasoning model with a 1M-token context window
inclusionAI, Ant Group's model team, published Ling-3.1-flash on Hugging Face under the MIT license, an upgraded native hybrid reasoning model with 560B total parameters, 25B active per token and a 1M-token context window, built on Ling-3.0-flash. It uses a hybrid-linear MoE design with 512 routed experts, 8 active, mixing KDA and gated MLA attention layers at 7:1. inclusionAI reports strong results on coding and agent benchmarks including Terminal-Bench 4.0, SWE-bench Pro, FrontierSWE and GDPVal-AA V2.1, and says it works in Claude Code, Kilo Code, Qwen Code, Hermes Agent and OpenClaw. A day-0 SGLang image serves it on 8x H200 or 4x GB300, and the team says it is considering open-sourcing LingCode, its long-horizon coding harness built on Pi.
- Ling 3.1 Flash lands in Cline, free until October 13
Cline announced Ling 3.1 Flash is now available in the editor and free until October 13, per the company's account.
- Ant announces Ling-3.1-flash: 560B total parameters, up to 1M token context
Ant Group announced Ling-3.1-flash on September 30: roughly 560B total parameters with about 25B activated, and context up to 1 million tokens, with a self-reported 1,673 Elo on GDPVal-AA v2.1. Per IT之家, it comes with a two-week free trial (256K context during the trial), opens the full 1M context after payment, and is planned for open sourcing — weights are not yet released.