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

User reports about 920 tokens/s prompt processing for Qwen3.8 Flash-Next MoE UD_Q3_XXL on two RX 7900 XTX cards, and about 1,600 tokens/s prompt processing for Qwen3.8 27B dense Q8_0 with tensor parallel. Setup is a custom llama.cpp RDNA3 fork with ROCm 7.14, adaptive MTP draft depth up to 3, Q8_0 KV cache, layer split, and MoE experts offloaded to system RAM with a 288-slot GPU-resident expert cache. The user notes the expert cache slows prompt processing to a crawl on their workload and they run with it disabled; with 288 experts they report a 95% hit rate and 45 t/s decode with MTP. The build is experimental and the figures are measured, not guaranteed.