Ling-3.0-flash-VL open weights released in BF16 and FP8

FellMentKE · x · 2026-09-10

Ling-3.0-flash-VL is now available as open weights in both BF16 and FP8, ready to plug into multimodal workflows. Hosted on Hugging Face and ModelScope.

Related event: Ant Group's inclusionAI Open-Sources Ling-3.0-flash-VL, a 124B Sparse MoE Vision-Language Model(9 posts)→

Original post →

More from Multimodal

Multimodal channel →