←Story detail

Trending story

Bailing releases and open-sources native multimodal model Ling-3.0-flash-VL

1 reports1 story updatesUpdated Sep 9 08:00

Understand this story

AI overview

On September 9, 2026, Ant Bailing released and open-sourced Ling-3.0-flash-VL, the first native multimodal large model in the Ling series. Built as an extension of the Ling-3.0-flash MoE architecture, the model has 124B total parameters and 5.5B activated per inference, natively supports image, text, and video inputs, and has a 256K-token context window. According to the company, native multimodal joint training improved the model's score on the Artificial Analysis Intelligence Index v4.1.1 by 4 points over the text-only version, and it introduces a visual feedback loop of observe, act, verify, and correct, used for front-end replication, GUI agents, and medical report interpretation. The model is currently available for free trial on Ling Studio, and the BF16 and FP8 versions have been open-sourced on Hugging Face and ModelScope.

AI-generated from public reports

Latest development · Report

Ant Ling Open-Sources Native Multimodal Model Ling-3.0-flash-VL

Developments

1 confirmed developments

  1. Bailing releases and open-sources native multimodal model Ling-3.0-flash-VL

    Source:English text is being prepared.

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Sep 9

  1. Ant Ling: Developer BlogFirst-partySelected

    Ant Ling Open-Sources Native Multimodal Model Ling-3.0-flash-VL

    Ant Ling has released and open-sourced Ling-3.0-flash-VL, the first native multimodal large model in the Ling series. Built as an extension of the Ling-3.0-flash MoE architecture, it has 124B total parameters and 5.5B activated per inference, natively supports image, text, and video inputs, and has a 256K Token context window. The company says native multimodal joint training improved the model's score on the Artificial Analysis Intelligence Index v4.1.1 by 4 points over the text-only version, and it introduces a visual feedback loop of observe, act, verify, and correct for front-end replication, GUI Agent, and medical report interpretation. The model is now available for free trial on Ling Studio, and the BF16 and FP8 versions have been open-sourced on Hugging Face and ModelScope.

Related stories

  1. Related storiesGoogle DeepMind releases Gemini 3.7 Flash
  2. Related storiesMeta releases open-weight model Muse Spark Open
  3. Related storiesStepFun Announces Financial Capability Evaluation of Step 5 Preview
  4. Related storiesEnglish translation is being prepared.