Qwen3.8 125B (6B active) Flash-Next Abliterated

User reports Qwen3.8-Flash-Next-GSQ-RCO-Abliterated at IQ3_S running with 12GB VRAM and 32GB system RAM, achieving 20-30 tok/sec decode and 300 to ~90 thousand tok/sec prefill on a custom fork of Strata. The Q2 quant achieves 39-45 tok/s decode. The fork has many experimental architectural changes. User compares the experience to local Opus on sub 2k compute.