News for hackers. Stuff that matters.
Re:Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling by hedgehog on Monday July 20, 2026 @03:10PM (#48983485)
No the weights are in the metal layers, they cannot be updated.
Re:Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling by jfim on Monday July 20, 2026 @07:15PM (#48986092)
The base weights can't be updated but from what I recall it allows adding a low rank adapter to customize the model a little bit.
Re:Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling by hedgehog on Tuesday July 21, 2026 @10:42AM (#48992971)
Yes that's what I've read. As far as I know the approach should transfer well to hybrid model architectures like modern Qwen and sizes like 27B by using multiple chips. LoRA-steered Qwen 27B at 10K+ tokens per second would be transformative for some workflows.