2.78 万亿参数,8GB 内存,单 CPU。 这个组合确实有点离谱。
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,8GB 内存,单 CPU。 这个组合确实有点离谱。 开源项目 kimi-k3-in-c,用 176KB 的可移植 C99 代码跑超大 MoE,不依赖 CUDA、PyTorch、BLAS,甚至不需要 GPU。 1️⃣ 896 个专家,每个 Token 只激活 16 个 2️⃣ 模型放 NVMe,剩余权重按需流式加载 3️⃣ 8GB 内存下生成一个 Token 约 26~32 秒 4️⃣ 不同内存配置下,输出结果保持字节级一致 当然,它目前更像一个极限条件下的技术实验,不是拿来日常聊天的。 但它证明了一件挺有意思的事:超大 MoE 模型,不一定非得整套塞进内存。 🔗 https://github.com/FareedKhan-dev/kimi-k3-in-c
Posted by lumxss (24.7k followers) 2 days ago · 119 likes · 11.6k 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
- 2.78 万亿参数,单 CPU,8.24GB 内存。 — @bkdgiffug
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.