{
  "id": 14794358,
  "title": "Janas: Run LLMs Bigger Than Your RAM by Streaming from SSD",
  "url": "https://urgent.news/2026/10/15/janas-run-llms-bigger-than-your-ram-by-streaming-from-ssd",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-15T21:22:56.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/unfiltered_anshul/janas-run-llms-bigger-than-your-ram-by-streaming-from-ssd-5al2"
  },
  "original_language": "en",
  "account": "Janas is a tool that allows developers to run large language models (LLMs) that exceed the capacity of their RAM by streaming the experts from an SSD. Launched in October 2026, Janas has been gaining popularity among developers who want to run large models locally without investing in expensive GPUs. The primary concept behind Janas is to stream the required experts from SSD during runtime, enabling the execution of models that normally demand 100GB of RAM on machines with only 16GB of memory. However, this approach comes at the cost of slower speed compared to RAM but is significantly faster than swapping to disk.",
  "summary": "What Is Janas Janas is a tool that runs LLMs bigger than your RAM by streaming expert models from SSD. It launched in October 2026 and has been quietly gaining traction among developers who want to run large models locally without buying expensive GPUs. The pitch is simple: instead of fitting the entire model in RAM, Janas streams the experts from SSD as needed. This means you can run models that…",
  "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."
}