capy-flash v0.7.1: Qwen3.8-Flash-Next (125B MoE) now runs in 64 GB of RAM (234 tok/s on two 16 GB cards), and Qwen3.8-27B 3-bit fits on a single 16 GB card (174 tok/s)
英文标题：capy-flash v0.7.1: Qwen3.8-Flash-Next (125B MoE) now runs in 64 GB of RAM (234 tok/s on two 16 GB cards), and Qwen3.8-27B 3-bit fits on a single 16 GB card (174 tok/s)
I've been building capy-flash, an open-source inference engine for running Qwen3.8-Flash-Next (125B MoE) and Qwen3.8-27B on consumer RTX 50 cards. Until now it needed my setup (two 16 GB cards and 96 GB of RAM) or better. v0.7 is about smaller machines: start with what you have, add a second card la
中文
I've been building capy-flash, an open-source inference engine for running Qwen3.8-Flash-Next (125B MoE) and Qwen3.8-27B on consumer RTX 50 cards. Until now it needed my setup (two 16 GB cards and 96 GB of RAM) or better. v0.7 is about smaller machines: start with what you have, add a second card la
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
I've been building capy-flash, an open-source inference engine for running Qwen3.8-Flash-Next (125B MoE) and Qwen3.8-27B on consumer RTX 50 cards. Until now it needed my setup (two 16 GB cards and 96 GB of RAM) or better. v0.7 is about smaller machines: start with what you have, add a second card la