Ask HN：普通硬件上的本地模型有朝一日能具备竞争力吗？
1 分•作者: locusofself•3 个月前
我有一台配备 24GB 内存的 Macbook Air M3。前几天，我第一次想在本地运行一个 LLM。我运行了 gemma-4-e4b，并向它输入了一些聊天内容。
这让我想起了我第一次使用 ChatGPT 的经历。虽然它显然不如 Opus 4.6 这样的模型强大，但它让我对未来充满了期待。
我知道拥有一个像样的 GPU 的普通人就可以运行相当强大的模型。
我真正的问题是，硬件和软件优化相结合，是否能让我们在真正基础的硬件上运行接近“state of the art”（最先进）的模型？
考虑到在数据中心上花费的巨额资本支出，如果出现类似摩尔定律的现象，或者其他算法突破，让我们能够运行在普通机器上的超级 LLM，会怎么样呢？
查看原文
I have a Macbook Air M3 with 24gb RAM. The other day, I wanted to try running an LLM locally for the first time ever. I ran gemma-4-e4b and threw some chats at it.<p>It reminded me of my very first experiences with ChatGPT a bit. Clearly less capable than something like Opus 4.6, but I made me excited about the possibilities.<p>I know that fairly capable models can be run by mere mortals who have a fancy GPU.<p>My real question is, will some combination of hardware and software optimizations get us anywhere close to "state of the art" models running on truly basic hardware?<p>With all the ridiculous capex being spent on datacenters etc, what if something akin to Moore's Law, or other algorithmic breakthroughs, will get us super capable LLMs that can run on the average machine?