Distilled DeepSeek into Gemma 4 26B-A4B vs 12B. Not very useful, but I learned a lot.

So I decided to learn how to fine-tune LLMs. Read a few guides from Unsloth, poked around, then stumbled on Unsloth Studio and wanted to test it out. The dataset I started from a set of relatively unrelated QA pairs — Natural Questions — and stripped the answers. Then I had DeepSeek v4 Pro (th

中文全文翻译正在补齐，可先查看下方英文原文。

So I decided to learn how to fine-tune LLMs. Read a few guides from Unsloth, poked around, then stumbled on Unsloth Studio and wanted to test it out. The dataset I started from a set of relatively unrelated QA pairs — Natural Questions — and stripped the answers. Then I had DeepSeek v4 Pro (th