Testing out Qwen 3.8 27B Q3_K_XL ~20tok/sec on a 2060 laptop + 3060 rig connected via rpc
96k context #AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️
There's nothing more infuriating than GPT-5.6 or Fable acting "morally superior" and refusing to do the work I assign them.
And it happens often... GPT-5.6 refusing: - To create content the way I say. - To create ad campaigns the way I want. - To advise or answer some
Qwen 3.8 max just ran an AI project for 10 days without a human.
And that’s not even the most impressive test Alibaba showed. What it actually did: → Started with an empty folder and built a working CLI tool from scratch → Created its own job queue, ran tests, caught
On the flight I tried MTPLX and ds4 with Qwen 3.8 Flash Next on M5 Max in Low Power.
Not bad! In ds4 I've not cooked support for MTP in ds4 chat. - MTPLX 25 t/s - DS4 18 t/s
You have reached the end of the archive
All of qwen38