I'm currently testing out Qwen3.8-27B using Unsloth's UD-Q4_K_XL running a freshly rebuilt llama.cpp. I have a 22GB RTX 2080TI on which I'm able to fit 100k context with q8_0 quantization, and using MTP with --spec-draft-n-max 4 I get about 40tk/s which is slightly less than Qwen3.6-27B but usable e
