https://village-sim-one.vercel.app/ - 16GB VRAM RTX 5070 Ti, fully offloaded - Vision on CPU - Windows, not headless - beellama.cpp - latest version with the kvarn performance enhancements making it as fast as qx_x quants. - MTP n-max = 2 - tg up to 75t/s, pp up to 1700t/s - KV = kvarn3/kvarn3 - MTP
