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

User compares Strata and Infernix running Qwen3.8-Flash-Next Uncensored on a single RTX 5090 32GB with 192GB system RAM on Windows 11. Infernix NVFP4 reaches 137.0 tok/s decode and 3,497 tok/s prefill at 512k context (YaRN 2), while Strata Q4_K_S gets 126.3 tok/s decode and 3,045 tok/s prefill at the same context. Setup uses int8 KV cache, MTP spec-4 with lm-head-draft, and a 52GB n-gram volume mmap'd from NVMe with 63.3 GiB of experts pinned in RAM. Decode was measured at roughly 39k effective context, with ±10-15 tok/s run noise. User reports Infernix is 23% faster at 262k and 9% faster at 512k, calls it the daily driver, and notes vision works on both engines.