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

User describes a Swift-based LLM harness built around Qwen 3.8 Flash-Next and Qwen 3.8 27B that adds a runtime slider to suppress prompt refusals without reloading or swapping to a separate abliterated model. The slider trades model coherence for reduced refusal, and lets the main agent spawn abliterated sub-agents. No hardware, engine, quant or context length is stated. MTP acceptance drops as the slider is raised, taking decode from 60-70 tok/s down to 20-30 tok/s.