Rohan Paul· @rohanpaul_ai · X·· 3 小时前AI 评分40
AI 导读
Emad Mostaque：AI 模型“几乎已经达到了人脑的效率”。 阿里巴巴的 Qwen 27B 通常需要约 60GB 内存，而 Prism ML 的一个团队通过用 1.5 位而非 16 位存储其数值，将其压缩到 6GB，同时保留了 95% 的性能。 在 6GB 下，它能跑在树莓派上，“其能耗和你的大脑一样。” ---- 完整视频在“Tom Bilyeu”YouTube 频道，（链接在评论中）
正文
Emad Mostaque: AI models "have pretty much reached the efficiency of a human brain".
Alibaba's Qwen 27B normally needs about 60GB of memory, and a team from Prism ML cut that to 6GB by storing its numbers with 1.5 bits instead of 16 while keeping 95% of its performance.
At 6GB it runs on a Raspberry Pi, "which uses as much energy as your brain."
----
Full video on "Tom Bilyeu" YouTube channel, (link in comment)
来源：Rohan Paul · x.com