649 2 weeks ago

DavidAU's uncensored multi-stage decensor of Qwen Team's Qwen3.8-27B: built-in MTP, native vision, 262K ctx (1M ext), thinking by default. Q4_K_M GGUF. Dual TITAN RTX @96.8K: 40 tok/s decode, acceptance 0.70. Cred: Qwen Team + DavidAU.

tools thinking