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: Moondream, a small vision language model that runs on 8GB of RAM

9 点作者 radq超过 1 年前
I&#x27;ve been working on training this small vision language model for the last month - excited to release the first prototype today! It is based on SigLIP (image encoder), Phi-1.5 (text model) and trained using the LLaVa-1.5 training dataset.<p>It runs reasonably fast on CPU with ~8GB of RAM in full 32-bit precision. There&#x27;s plenty of room to speed it up and reduce memory consumption by quantizing the model.<p>I posted a video of it running on my M2 Macbook Air (on CPU not MPS, so performance should be comparable on other hardware) on Twitter to demonstrate inference speed: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;vikhyatk&#x2F;status&#x2F;1740910503323734448" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;vikhyatk&#x2F;status&#x2F;1740910503323734448</a>

暂无评论

暂无评论