Nathan Lambert· @natolambert · X·· 2026-04-04精选
AI 导读
开源模型成功的核心并非基准分数，而是即时且长期的工具支持与可微调性。Gemma 过去在这些方面表现挣扎，而 Qwen 则表现出色，这才是决定模型成败的关键因素。
推荐理由
HF研究员指出开源模型成功关键在工具链与微调支持而非基准分数
正文 · 原文
People are too obsessed with benchmarks for open models. The core determining factor of success often is:
1. Immediate & long term tooling support.
2. Finetunability
Tbh Gemma has struggled here in the past. Qwen has excelled at it. It's where the winners are crowned. https://t.co/LkGb3tHjA3
Gemma 4 and what makes an open model succeed Hint: it's not benchmark scores. https://www.interconnects.ai/p/gemma-4-and-what-makes-an-open-model在 X 查看被引用的帖子
来源：Nathan Lambert · x.com