Unknown family

User reports about 82 tokens/s average decode speed from 8K through 72K context on an RTX 5070 Ti 16GB. Setup is a llama.cpp fork with Adaptive KV Streaming V2 and MTP draft length 3, keeping an effective decode KV pool of around 2.2 GiB even at 256K context. Decode speed drops to about 35 t/s at 144K, 30 t/s at 192K, and 19 t/s at 256K. The user notes MTP requires the same K/V quantization as the main model.