{
  "id": 18933606,
  "title": "Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU",
  "url": "https://urgent.news/2026/11/08/llama-modchip-284b-deepseek-on-64gb-ram-no-gpu",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-08T10:22:04.000Z",
  "source": {
    "name": "Hacker News",
    "slug": "hacker-news",
    "url": "https://github.com/synchopate/llama-modchip"
  },
  "original_language": "en",
  "account": "The llama-modchip project enables running a 284 billion parameter Frontier Model of Expert (MoE) on a 64GB CPU workstation without any GPU hardware. This is achieved through a combination of advanced compression techniques, including Analytical SwiGLU-H2 Second-Order Hessian Compression, Fractal-64 Q2_0, and L1D/L2/L3 cache optimizations. The tool also includes features like 4-Level Register, L2 Quadrature MoE Pruning, and zero-API Claude Code to accelerate inference speeds. The system successfully runs models like DeepSeek-V4-Flash (59GB RAM, 44.4 tokens per second) and Nemotron-3.5-30B-A3B (25-111 tok/s) while maintaining a 256K context window. This breakthrough makes large-scale AI models accessible for local, air-gapped use on standard hardware, eliminating the need for expensive multi-GPU setups.",
  "summary": null,
  "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."
}