News for hackers. Stuff that matters.
Re:Qwen3.5: Towards Native Multimodal Agents by regularfry on Monday February 16, 2026 @10:01AM (#47035866)
They're claiming 20+tps inference on a macbook with the unsloth quant.
Re:Qwen3.5: Towards Native Multimodal Agents by embedding-shape on Monday February 16, 2026 @12:48PM (#47037930)
Yeah, I'm guessing the Mac users still aren't very fond of sharing the time the prefill takes, still. They usually only share the tok/s output, never the input.