Hackernews posts about K2 1T

  1. 768GB Intel Optane DIMMs to run 1T-parameter LLM with single GPU at 4tps (www.tomshardware.com)
    30 points by walterbell 22 days ago | 2 comments
  2. 768GB of cheap DIMM memory used to run 1T-parameter LLM on single GPU (www.tomshardware.com)
    2 points by doener 28 days ago | discuss
  3. Kimi K2 1T model runs on 2 512GB M3 Ultras (twitter.com)
    234 points by jeudesprits 6 months ago | 121 comments
  4. Kimi-K2-Thinking 1T at 28 tok/SEC with MLX tensor parallel (twitter.com)
    5 points by jeudesprits 6 months ago | 1 comments
  5. Kimi K2: 1T total parameter open-source LLM by Moonshot AI (huggingface.co)
    4 points by cyp0633 12 months ago | discuss
  6. Kimi K2 1T model (4-bit quant) 2x512GB M3 Ultras with mlx-lm and mx.distributed (xcancel.com)
    1 points by _____k 6 months ago | discuss
  7. Kimi K2.5 1T runs on 2 M3 Ultras with mlx-lm in it's native precision (twitter.com)
    5 points by jeudesprits 5 months ago | discuss
  8. Show HN: Kimi K2.5 (Agent Swarm, beats GPT-5) now on RouterLab (Swiss hosting) (routerlab.ch)
    1 points by ScioNos 5 months ago | discuss