Ran Qwen3.8-Flash-Next (79 GB, 2-bit) at 350K ctx for 3.5 hours on a 128 GB M5 Max — speed vs context depth, 100 turns, one graph

A user successfully ran Qwen3.8-Flash-Next (79 GB, 2-bit) with a 350K context for 3.5 hours on a 128 GB M5 Max MacBook Pro. The setup utilized llama.cpp b10686 with Metal and a 358,400-token context slot via YaRN. Performance was strong for the first 100K context, but beyond that, the model exhibited role confusion, mixing user messages with its own output. Suspects for this degradation include the 2-bit quantization or the preview model's long-context quality.