Qwen3.5 0.8B on CPU

Since the Qwen3.5 0.8B model is an interesting one for small specialized fine tunes, I was curious how fast it can run on CPUs. Why CPUs? Mainly because I want to use it as a local dictation cleanup model when I'm using the GPU for something else. Over the weekend, I let Codex build a small C++ engi

中文全文翻译正在补齐，可先查看下方英文原文。

Since the Qwen3.5 0.8B model is an interesting one for small specialized fine tunes, I was curious how fast it can run on CPUs. Why CPUs? Mainly because I want to use it as a local dictation cleanup model when I'm using the GPU for something else. Over the weekend, I let Codex build a small C++ engi