{
  "id": 2279139,
  "title": "Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference",
  "url": "https://urgent.news/2026/08/20/daedalus-150m-a-convolution-attention-hybrid-designed-for-cpu",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-20T16:09:43.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.20210v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one user, one token at a time, 4-bit weights, ordinary CPU, and chose the architecture to suit it. The result keeps full attention in only 6 of its 18 blocks. The other 12 use short convolutions whose memory is two timesteps wide no matter how long the…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}