Qwen3.6 27B

User reports Qwen 3.6 27B at 23.66 tok/s decode on a Tesla P40 24GB. Setup is llama.cpp with IQ4_XS GGUF, turbo3 KV cache, MTP self-speculative decoding (N=2, p_min=0.5), 65536 context, single card. MTP accept rate 83.7%, a +28.0% gain over the non-MTP Q4_K_M baseline at 18.48 tok/s. A cache sweep found turbo3 best at 22.43 tok/s and 18.1 GB VRAM, while q8_0 broke MTP with 0% draft acceptance.