Xolotl (Strata based) - DeepSeek-V4.1-Flash (552B) on a single 4090 at ~27 tok/s, Uncensored 1017 quant coming in a couple of days

Hey all, been meaning to post this for a while. I've been building an inference engine based off Strata called Xolotl that runs DeepSeek-V4.1-Flash, all 552B of it, on one gaming PC. My setup is a single RTX 4090 (24GB), a Ryzen 7 5700X, 90GB of DDR4 and an NVMe drive, nothing fancy. The weights get

中文全文翻译正在补齐，可先查看下方英文原文。

Hey all, been meaning to post this for a while. I've been building an inference engine based off Strata called Xolotl that runs DeepSeek-V4.1-Flash, all 552B of it, on one gaming PC. My setup is a single RTX 4090 (24GB), a Ryzen 7 5700X, 90GB of DDR4 and an NVMe drive, nothing fancy. The weights get