Qwen 3.8 27B Abliterated is live on NEAR AI Cloud.
Refusals removed, for red teaming and security research, with vision. It runs in a TEE, so your findings stay private. $0.04/M input, $1.35/M output, 256K context. Try it free:
How many separate apps does your local AI setup take right now?
Chat in one, ComfyUI in another, a coding agent in a third? Locally Uncensored puts all of it in one desktop window. It's a free, open-source (AGPL-3.0) app for Windows and Linux, with a macOS beta for Apple silicon
Qwen 3.8 27B built my city at night at 65 tok/s.
Every window was piled at the origin. Same prompt on three stacks. DeepSeek V4.1 Flash on the 4 box Spark ring hit 120.74 tok/s. GLM 5.3 Flash on TensorFold 0.6.0 TP4 hit 108.0 tok/s. Qwen 3.8 27B on the Mac Studio alone hit 65.23
Man, would you be so kind to run the Burj Al Arab test again?
Reaaaaally would like to compare it to my Qwen 3.8 Flash result. This one was created with Unsloth's Q6_K_XL using the DeepSeek Harness.
You have reached the end of the archive
All of qwen38