ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Alibaba's Qwen released Qwen3.8 open weights under Apache 2.0, including Qwen3.8-27B and the larger Qwen3.8-2.4T-A95B. The models handle 262,144 tokens natively, scaling to one million via YaRN, and are available on Hugging Face and ModelScope.
Tracked by ByteBrief