{
  "id": 18385845,
  "title": "How much memory does a local LLM need?",
  "url": "https://urgent.news/2026/11/05/de-combien-de-memoire-un-llm-local-a-t-il-besoin",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-05T22:24:44.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/bestaitools-fr/de-combien-de-memoire-un-llm-local-a-t-il-besoin--a97"
  },
  "original_language": "fr",
  "account": "An article discusses estimating the memory required to run AI models locally. The estimation involves calculating the model's weights, KV cache, and overhead, and comparing it to the device's available memory. For example, a 14B model in Q4_K_M requires around 8-9 GB of memory, with an estimated 8.4 GB displayed by the osFoundry desktop application on a 16 GB MacBook M3. The article provides guidelines for determining whether a model can run on a device based on its memory usage and estimated generation speed.",
  "summary": "Before downloading a model to run it locally, you need to know if it will fit in memory. The estimate is the sum of three terms, compared to what the machine can actually give to the model: need = weights + KV cache + overhead fits if need ≤ 0.8 × usable memory The figures below follow the estimation used by the local model browser of the desktop application…",
  "key_points": [
    "Local LLM memory needs determined by weights, KV cache, overhead",
    "14B model in Q4KM quantization requires 8-9 GB total",
    "Memory must be less than 80% of usable memory on system"
  ],
  "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."
}