Your phone got power with superintelligent
Locally Qwen 3.8 27B on a 3090, over Tailscale. agent designing a camera app with Live preview, capture, filters, zoom, vision for object detection, 155 tok/s prompt, 51 tok/s generate,
This is my version of the same prompt made by Qwen 3.8 Q4_K_XL reasoning low, on 2x3090 24gb.
It took 13 mins to complete, and 36k tokens context.
Companies are moving AI in-house for control and privacy, fueling growth in local AI options.
Qwen 3.8 27B now offers unprecedented local intelligence, a game-changer for software development.
Same prompt on Qwen 3.8 Q4_K_XL reasoning low 13 mins on 2x3090 24gb.
It took 36.9k tokens.
You have reached the end of the archive
All of qwen38