Qwen3.8 27B
on AMD RX 9070 · llama.cpp · 131,072 ctx
Summary
User reports Qwen3.8-27B-UD-IQ3_XXS.gguf at 40.68 t/s generation and 778.91 t/s prompt processing at 131,072 context, against 13.36 t/s and 137.87 t/s at 65,536 context.
Setup is llama-server with flash-attn, a q8_0 KV cache, Vulkan0, and speculative decoding with draft-mtp and ngram-mod.
User asks why the smaller context degrades performance.