A 27B model with its whole trained context window, at q80 KV precision, on one RTX 4070 12 GB. 78 tok/s of new text at 32k tokens of context (175 on code), 69 at 64k, 61 at 112k, and the window keeps going to 262k. Lossless speculative decoding at every depth. A server that answers the requests agents and apps actually send. One command on Windows. This is PrismML's Ternary Bonsai 2 27B (1.58-bit ternary PTQ10, 5.9 GB, Apache 2.0), the same weights, nothing re-quantized, with its MTP draft head grafted back on (byte-identical trunk, proof below) and the serving stack from github.com/professorpalmer/bonsai-ada-surgery: a tiered KV cache that puts the first ~119k positions in VRAM and the…