News for hackers. Stuff that matters.
Re:Qwen4-Max by gardnr on Monday November 16, 2026 @12:50AM (#50514468)
Re:Qwen4-Max by nout on Monday November 16, 2026 @02:06AM (#50514877)
The openai reference there is interesting
Re:Qwen4-Max by HenryMulligan on Monday November 16, 2026 @10:11AM (#50518440)
Doesn't that just refer to using the OpenAI response/completion/etc. API? Just about everybody (llama.cpp, vLLM, etc.) supports that. I think the reference to "qwen4.5-max" is more interesting myself.