@AdinaYakup: Yes https://huggingface.co/collections/Qwen/qwen38-flash-next…
Summary
A new multimodal AI model, Qwen3.8-Flash-Next-FP8, is released on Hugging Face with 180 billion parameters, supporting image-text-to-text tasks as part of a Qwen collection.
View Cached Full Text
Cached at: 08/26/26, 01:14 PM
Yes https://huggingface.co/collections/Qwen/qwen38-flash-next…
Qwen3.8-Flash-Next - a Qwen Collection
Source: https://huggingface.co/collections/Qwen/qwen38-flash-next
#### Qwen/Qwen3.8-Flash-Next-FP8 Image-Text-to-Text• 180B• Updatedabout 1 hour ago • 451 • 34
Similar Articles
Qwen3.8-Flash-Next
Qwen has released Qwen3.8-Flash-Next, an open-weights multimodal MoE model with 125B tokens but only 6B active parameters, providing a performance boost and serving as an early preview of the Qwen4 architecture.
Qwen/Qwen3.8-Flash-Next
Release of Qwen3.8-Flash-Next, an open-weight AI model introducing architectural innovations like Hybrid Attention with QSA and Gated Residual for improved efficiency and scalability, previewing the future Qwen4 architecture.
@AdinaYakup: Open source summer party is not over yet https://huggingface.co/Qwen/Qwen3.8-27B…
Qwen3.8-27B, a compact 27B dense vision-language model with flexible thinking control and long-context support, is released as the most capable Qwen open model to date, available soon via Hugging Face and Qwen Cloud.
@AdinaYakup: Qwen @Alibaba_Qwen just dropped a new Text to Image benchmark + a judge model https://huggingface.co/collections/Qwen/q…
Qwen released a new Text-to-Image benchmark with 56 fine-grained evaluation facets, measuring creativity beyond prompt alignment, and includes a human-aligned judge model.
Qwen3.7 Preview lands on Arena (1 minute read)
Alibaba Qwen announces two major model releases: Qwen3-Omni, the first natively end-to-end omni-modal AI unifying text, image, audio and video, and Qwen3-Next-80B-A3B, an ultra-efficient MoE model with 3B activated parameters per token, achieving SOTA performance and 10x faster inference than Qwen3-32B.