←Back to NewsAI News/ImagemodelImageLlmsAnt Group's Ling-3.0-flash-VL Brings Images and Video to Its 124B Open ModelInclusionAI open-sources a 124B-parameter mixture-of-experts vision-language model with 5.5B active parameters, 256K context, and MIT license.SourceAlphaSignalPublishedSep 4, 2026, 3:24 PMAuthorAlphaSignal NewsroomRead1 min readInclusionAI open-sources a 124B-parameter mixture-of-experts vision-language model with 5.5B active parameters, 256K context, and MIT license.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsAlphaSignal · modelJapan's LLM-jp-4-VL 9B Beats InternVL on Japanese While Staying Truly Open SourceDeepSeek · modelDeepSeek's V4-Flash-Vision-Exp Adds Image Understanding at Half the Cost of RivalsQwen · newsAlibaba's Qwen3.8 LiveTranslate Cuts Speech Translation Lag to 2.3 Seconds
