2.78 万亿参数，单 CPU，8.24GB 内存。
This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
2.78 万亿参数，单 CPU，8.24GB 内存。 这个 kimi-k3-in-c 项目看着就很离谱：只用 176KB 可移植 C99 代码，不依赖 BLAS、PyTorch、CUDA，也不需要 GPU。 它把 1.56TB 模型检查点放在 NVMe 上，只激活部分 MoE 专家，其余参数按需加载，避免全部塞进内存。 8GB 内存下生成一个 Token 大约要 26～32 秒，所以目前更像技术验证，而不是日常聊天工具。 最有意思的是：内存预算不同，速度会变，但输出结果可以保持字节级一致。 代码也很精简，源码树只有约 45MB。 🔗 https://github.com/FareedKhan-dev/kimi-k3-in-c
Posted by lumxss (24.7k followers) 3 h ago · 3 likes · 683 views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: kimi-k3-in-c.
More dev work like this
- Large Vision Model! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM… — @gp_pulipaka
- Building a WhatsApp automation bot shouldn’t mean wiring every command into the core. — @DanKornas
- 🤯牛哇！开源圈把 Jev 的「系统一」快思考范式复刻到这个程度了，SemIf 在 JevBench 上 74.7 分，几乎贴着官方 Jev 1.13.0 的… — @NFT_Chen
- I have previously said this: You don't pick an inference engine first. You pick a… — @TheAhmadOsman
- Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the… — @alibaba_cloud
- Jev pod tomorrow — @swyx
- 😂笑死！Jev 刚出一周，中文圈圈已经把命名权当地皮抢完了，Jev-Anything！ — @NFT_Chen
- Maestro v2.3 is out! — @blizaine
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 18.9k posts from 4.9k X accounts over the last 21 days, 2.1k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 06:12 UTC. Full method.