{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiagbtulxuu4iie6y5webjy37ljvq4cw77adr5qinl4mzbtfinusry",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mpr2deqznqr2"
  },
  "path": "/t/which-open-source-llm-are-you-currently-using-for-chatbot-development-and-why/176980#post_2",
  "publishedAt": "2026-07-03T16:47:28.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Hi Suhebmultani,\n\nI’m currently using Llama 3 running locally on Ollama.\n\nThe main reason for this choice is that it’s a solid, “good enough” model that works perfectly with the hardware I have: i7 CPU, 32 GB RAM and RTX 5060 Ti with 16 GB VRAM.\n\nI can load the model entirely into the GPU and still have plenty of room for the chatbot’s context window. It provides great performance for development and interaction.",
  "title": "Which open-source LLM are you currently using for chatbot development and why?"
}