{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiernqy4ef7yh6maxz6665t7sz5k2qho5npuntx5pzderrcx4pqpiu",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mm4abnujwrh2"
  },
  "path": "/t/embedding-a-local-llm-directly-into-an-indie-interrogation-game/176074#post_3",
  "publishedAt": "2026-05-17T23:30:26.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Yeah, I’ve been thinking about separating the model from the main game build for exactly those reasons.\n\nRight now I prioritized a “just launch and play” approach with everything bundled together, but it definitely creates problems for updates and lower-end PCs.\n\nSupporting multiple model options depending on hardware would also be really interesting in the future.\n\nStill experimenting with the balance between accessibility and flexibility.",
  "title": "Embedding a local LLM directly into an indie interrogation game"
}