问 HN：自托管模型怎么了？
3 分•作者: curiousaboutml•6 个月前
HN 大家好，很抱歉用匿名账号发帖。<p>在我看来，直到去年年初，我们几乎每周都能看到几个新的“开放”模型发布公告。这些模型会为爱好者在笔记本电脑或家用服务器上运行的模型设定新的技术水平。<p>Meta、Deepseek、Mistral、Qwen，甚至 Google 等公司都在不断发布新模型。出现了新的格式、量化方法、推理引擎等等，最重要的是，围绕这些模型有很多讨论和兴奋。<p>但这种状况悄无声息地突然改变了。在 gpt-oss 发布（2025 年 8 月）之后，讨论的重点就一直集中在托管模型上。我认为在过去 6 个月里，我从未在任何登上 HN 首页的讨论中看到过 Ollama 的身影。<p>这是怎么回事？这是否意味着我们已经遇到了 LLM 效率的瓶颈？
查看原文
Hi HN, sorry for using a burner account.<p>It seems to me that up until the beginning of the last year, we saw a couple of new "open" model release announcements almost every week. They'd set a new state of the art for what an enthusiast could run on their laptop or home server.<p>Meta, Deepseek, Mistral, Qwen, even Google etc. were publishing new models left and right. There were new formats, quantizations, inference engines etc. and most importantly - a lot of discourse and excitement around them.<p>Quietly and suddenly, this changed. After the release of gpt-oss (August 2025), the discourse has been heavily dominated around hosted models now. I don't think I've seen any mention of Ollama in any discussion that reached HN's front page in the last 6 months.<p>What gives? Is this a proxy signal that we've hit a barrier in LLM efficiency?