一个 2.78 万亿参数的模型，单靠一颗 CPU 加 8GB 内存就能带起来，这事你敢信？
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
一个 2.78 万亿参数的模型，单靠一颗 CPU 加 8GB 内存就能带起来，这事你敢信？ 我刚看到的时候也直犯嘀咕。Kimi K3，推理部分用纯 C99 手写，BLAS 不沾、框架不碰、GPU 也不用。 硬盘上堆着 1.56TB 的权重，实际跑起来峰值内存只占 8.24GB，引擎本体才 176KB。 内存给得越多，差别只在快慢： 1️⃣ 普通笔记本 8GB，蹦一个 token 要 26.5 秒 2️⃣ 128GB 往上，压到 5.6 秒 妙就妙在答案完全一致，一个 byte 都不带差的，变的只是你干等的时间。 想上手折腾的，代码自己拉 🔗 https://github.com/FareedKhan-dev/kimi-k3-in-c
Posted by lumxss (33k followers) 1 days ago · 18 likes · 2.7k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: kimi-k3-in-c.
More dev work like this
- 长PDF要是拆成单页再往一块拼，跨页表格和阅读顺序十有八九会乱套，这事你八成也烦过。 — @bkdgiffug
- Local models on Apple Silicon finally feel like a product, not a weekend project. — @PixelRainbowNFT
- GPT 6.1 Terra max vs GPT 6.1 Sol max — @HarshithLucky3
- Asked at the Meetup: "Does sbx run mistral work?" — @ajeetsraina
- Most agents freeze once deployed. — @GoogleCloudTech
- Your $250 GPU can now run a 35B coding model at 50 tokens/sec. — @0x0SojalSec
- Next week we're showing how to build self improving products. — @spenserskates
- Seedance 2.5 US Draft mode is now available on fal — @fal
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 22:17 UTC. Full method.