TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Llama2.c on a Commodore C64

10 点作者 AMICABoard3 个月前
Warning: Inference takes ages.<p>Pics &amp; Media: <a href="https:&#x2F;&#x2F;x.com&#x2F;VulcanIgnis&#x2F;status&#x2F;1893420241310335329" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;VulcanIgnis&#x2F;status&#x2F;1893420241310335329</a>

3 条评论

HenryBemis3 个月前
&quot;How this works&quot; - Slowly!<p>I was chatting with ChatGPT 4o the other day and I was asking it on &quot;what steps&#x2F;software&#x2F;tools&#x2F;etc. I need to set up my own LLM offline on a PC&quot;.<p>I suggested a few PCs I got, they were all super slow, but for the purpose I want it (numerical analysis) I can make it work. But even my stupid old PCs are times-infinity faster than this C64!!
评论 #43177413 未加载
desertkun3 个月前
I once tried to slap TLS&#x2F;SSL stack onto ZX Spectrum – so HTTPS connection on it worked, but it took solid two minutes to just load a certificate – sometimes you gotta do the &quot;I made a screaming robot - why? - hmmmmmm....&quot;
评论 #43144550 未加载
评论 #43143920 未加载
Cheyana3 个月前
“No? Well, now you can!”<p>Lol, I’m stealin’ that.
评论 #43148109 未加载