@Chinazhidx: Ant Group just released Ling-3.0-flash • 124B MoE • 5.1B active params/token • 256K context, expandable to 1M Just 1/8 …
Summary
Ant Group released Ling-3.0-flash, a 124B MoE model with 5.1B active parameters per token and 256K context expandable to 1M, matching or outperforming their 1T flagship model on most benchmarks.
View Cached Full Text
Cached at: 07/24/26, 07:17 PM
🔥Ant Group just released Ling-3.0-flash
• 124B MoE • 5.1B active params/token • 256K context, expandable to 1M
Just 1/8 the total and 1/12 the active parameters of Ant’s 1T flagship model—yet matches or outperforms it on most benchmarks. #AntLing https://t.co/Rycwi6GoVC
Similar Articles
@10xmylife: 蚂蚁百灵发模型，Ling-3.0-flsh，从这个榜单来看还不错
Ant Group releases Ling-3.0-flash, a hybrid-reasoning MoE model with 124B total parameters and only 5.1B active per token, matching the performance of its 1T flagship model on most benchmarks.
Ling-3.1-flash: ~560B total params, ~25B active/token, up to 1M-token context- Free trail for 2 weeks then open source
Ling-3.1-flash is a ~560B-parameter MoE model with only ~25B active parameters per token and up to 1M-token context, offered with a 2-week free trial before being open-sourced.
Ant Ling just announced a second model today: Ling-3.0-flash-Sante (124B, 5.1B active)
InclusionAI (Ant Group) announced Ling-3.0-flash-Sante, a 124B-parameter (5.1B active) healthcare-focused model with a 256K context window for medical reasoning, literature research, and tool-assisted workflows, with weights released on Hugging Face.
@AdinaYakup: Ant Group just shipped Ling-3.1-flash New hybrid reasoning MoE model from @TheInclusionAI - 560B/25B active - MIT licen…
蚂蚁集团发布 Ling-3.1-flash，一款混合推理 MoE 模型，560B 总参数/25B 激活参数，采用混合线性 MoE 架构（KDA + 门控 MLA），支持 1M 上下文，并以 MIT 许可证开源。
@NousResearch: Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters an…
AntLingAGI releases Ling-3.0-flash, a 124B-parameter MoE model with 5.1B active parameters, now free for a week on Nous Portal. It matches or beats their 1T flagship on many benchmarks, designed for agent workloads like coding and tool use.