Qwen3-30B-A3B-2507 family is an absolute beast. The reasoning models are seriously chatty in their chain of thought, but the results speak for themselves. I’m running a Q4 on a 5090, and with a Q8 KV quant, I can run 60k token context entirely in vram, which gets me up to 200 tokens per second.

Fun speculation: we are CPUs for the information systems we inhabit, like scientific method, political ideologies, etc.

It’s trivial to get LLMs to act against the instructions

There is a lot more that goes into it than just being correct. 18000 waters may have been the actual order, because somebody decided to screw with the machine. A human who isn’t terminally autistic would reliably interpret that as a joke and would simply refuse to punch that in. The LLM will likely do what a human tells it to do, since it has no contextual awareness, it only has the system prompt and whatever interaction with the user it had so far.