← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

kimi-k3-in-c

github.com

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

라이브러리오픈소스

github.com 방문외부 사이트GitHub11,400 스타외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. A new engine to run Kimi K3 on a laptop

    Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights.

    Hacker News7점news.ycombinator.com최근 반응

  2. Warp

    Run DeepSeek v4.1 Flash with 5 GB of RAM at 3.77 tok/s

    Hacker News16점GitHub스타 2,546github.com오픈소스반응 3개최근 반응

  3. Kimi K3

    The world's first open 3T-class model

    Hacker News2,107점Product Hunt추천 438kimi.com반응 5개최근 반응

  4. Kimi K2

    The 1T parameter open model for agentic intelligence

    Hacker News5점Product Hunt추천 344moonshotai.github.io반응 2개최근 반응

  5. I implemented the Kimi K3 paper from scratch in PyTorch

    Independent from-scratch implementation of the Kimi K3 architecture (arXiv:2607.24653v1): KDA, NoPE, latent-space MoE, and the systems co-designs. Table 1 reproduced to 0.09%.

    Hacker News10점GitHub스타 43github.com오픈소스반응 2개최근 반응