Unsloth 发布 Kimi K3 本地运行版，1-bit 量化后体积缩减 62%
Kimi K3 can now be run locally! ✨
Unsloth 宣布 Kimi K3 现已可在本地运行，其 1-bit 量化版本体积从 1.56TB 压缩到 594GB，缩减 62%，精度保留约 78.9%，可在配备 128GB 内存的 Mac Studio 上运行。Unsloth 同时提供了使用指南和 GGUF 文件链接，并称 Kimi K3 是目前最强的开源模型。
查看原帖Introducing Kimi K3: Open Frontier Intelligence 🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal 🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts 🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost 🔹 Built for long-horizon agentic coding and self-evolving workflows Kimi…
展开完整原文
Introducing Kimi K3: Open Frontier Intelligence 🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal 🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts 🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost 🔹 Built for long-horizon agentic coding and self-evolving workflows Kimi K3 is now live on on https://t.co/zrk6zZxZUo, Kimi Work, Kimi Code, and the Kimi API. Open Weights by July 27, 2026. 🔗 API: https://t.co/XCrgjXAqMw 🔗 Tech blog: https://t.co/YTfiMSNM1f
正文
当前显示原文，中文全文译文尚未就绪。
Kimi K3 can now be run locally! ✨
The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).
Run on a Mac Studio + 128GB RAM device.
Kimi K3 is the strongest open model to date.