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 lab released Qwen 3.8 27B, an Apache 2 licensed vision-capable LLM with tool calling. The 17GB Q4_K_M quantized build runs locally, but defaults to xhigh reasoning effort, causing overthinking that exhausts context limits on consumer hardware.
Tracked by ByteBrief