I tested freshly merged DFlash in llama.cpp on Qwen 3.6 27B Local AI win. 4.44x faster at 36K context. Here are my findings RTX 6000 PRO.

Hey guys, A month ago I posted my MTP benchmarks here (3.34x on Gemma 4). DFlash support just merged into llama.cpp (PR #22105), so I ran it on the same rig with the Qwen 3.6 27B and it beat my best MTP numbers at every draft length. DFlash is speculative decoding with a block diffusion drafter from z-lab. Instead of drafting tokens one by one, it fills a block of 15(currently limit) tokens in a single pass. You can get the docker compose from repo and run it on your hardware as Llama server in one click to