Understand this story
On August 20, 2026, Ant Ling officially open-sourced two Base Models, Ling-3.0-tiny-base and Ling-3.0-flash-base, and simultaneously released the weights for three stages—pre-training, mid-training, and WSM merging—totaling 6 checkpoints. Official information shows that Ling-3.0-tiny-base has 7.9B total parameters and 1.3B activated parameters; Ling-3.0-flash-base has 124B total parameters and 5.1B activated parameters. Both models can be used for continual pre-training, supervised fine-tuning, preference optimization, reinforcement learning post-training, and distillation. The official announcement also notes that the Base Models have not completed instruction alignment, and it is not recommended to deploy them directly as end-user-facing chat services without post-training. Currently, there are no subsequent developments regarding this event.
AI-generated from public reports
Latest development · Report
Ant Ling Open-Sources Ling-3.0-tiny-base and Ling-3.0-flash-baseDevelopments
1 confirmed developments
Ling-3.0-tiny-base and Ling-3.0-flash-base are officially open-sourced
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Aug 20
Ant Ling: Developer BlogFirst-partySelected
Ant Ling Open-Sources Ling-3.0-tiny-base and Ling-3.0-flash-base
Ant Ling has officially open-sourced two Base Models, Ling-3.0-tiny-base and Ling-3.0-flash-base, and simultaneously released the weights from three stages—pre-training, mid-training, and WSM merging—for a total of 6 checkpoints. Ling-3.0-tiny-base has 7.9B total parameters and 1.3B activated parameters, while Ling-3.0-flash-base has 124B total parameters and 5.1B activated parameters; both can be used for continued pre-training, supervised fine-tuning, preference optimization, reinforcement learning post-training, and distillation. The official notes state that the Base Models have not completed instruction alignment and are not recommended for direct deployment as end-user-facing chat services without post-training.