Show HN： 扭曲 – 运行 313BGLM-5.3-闪光灯在一个MacBook带有8GB RAM
几个月前，我创建了WARP引擎（原名WASTE) 在 macOS 上运行 Kimi K3，即完整的 2.78 万亿参数模型。<p>GLM-5.3-Flash 与 Kimi K3 在架构上有许多相似之处，所以我也为它添加了支持。它最低只需要 5.14GB的RAM去跑，在64上GB MacBookPro M5 Pro 的速度大约为每秒 3.32 tok，或在较长运行中为每秒 3.86 tok。<p>更多的内存意味着更大的专家缓存，而更高的存储和内存带宽可以进一步提高性能。
查看英文原文
Show HN: Warp – Run the 313B GLM-5.3-Flash on a MacBook with 8GB RAM
A few months ago, I created the WARP engine (formerly WASTE) to run Kimi K3, the complete 2.78-trillion-parameter model, on macOS. GLM-5.3-Flash shares many architectural similarities with Kimi K3, so I added support for it as well. It requires as little as 5.14 GB of RAM to run, and on a 64 GB MacBook Pro M5 Pro it reaches about 3.32 tok/s, or 3.86 tok/s on longer runs. More memory means a larger expert cache, while higher storage and memory bandwidth can further improve performance. The project is completely open-source and free to use: https://github.com/sqliteai/warp
Show HN: Warp – Run the 313B GLM-5.3-Flash on a MacBook with 8GB RAM
A few months ago, I created the WARP engine (formerly WASTE) to run Kimi K3, the complete 2.78-trillion-parameter model, on macOS.<p>GLM-5.3-Flash shares many architectural similarities with Kimi K3, so I added support for it as well. It requires as little as 5.14 GB of RAM to run, and on a 64 GB MacBook Pro M5 Pro it reaches about 3.32 tok/s, or 3.86 tok/s on longer runs.<p>More memory means a larger expert cache, while higher storage and memory bandwidth can further improve performance.<p>The project is completely open-source and free to use: <a href="https://github.com/sqliteai/warp" rel="nofollow">https://github.com/sqliteai/warp</a>
- 来源
- Show HN · show-hn
- 证据角色
- project_and_comment_discovery
- 时间状态
- known
- 用户判决
- 未判