Strata is the shit

Have been using qwen 3.8 flash next with llamaserver. Was getting 70-80tk/s decode and was happy. Then read about strata and decided to give it a try. Decode shot up to 150 tk/s. Not sure what magic it's using? You should give it a try if you are still running qwen flash next on llamacpp. Also the tried DeepSeek v4.1flash 2.25bit and it's 70tk/s decode. Unsloth 6 bit quant 160k context 1 pro 6000 + 2 x 3090 256G ddr4