{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihzexp2p4pklhlpblwmgnhselu7rr6fomxkjul7k6tajjcl57j7ra",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mmlovkznmpy2"
  },
  "path": "/t/why-qwen-is-dynamically-stable-an-empirical-phase-map-of-10-llms/176177#post_2",
  "publishedAt": "2026-05-24T09:04:50.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Back when DeepSeek was making headlines in the general news, I often heard people on Discord say that Qwen was the easiest to work with as a student model for LLMs. As for teacher models, back then it was DeepSeek or various other commercial LLMs…\n\nI think Qwen was version 2.5 at the time, but I don’t think even the current version of Qwen has lost that characteristic. Qwen series tends to retain its original capabilities even after fine-tuning… though I don’t use it that heavily myself, so this is just my personal impression.\n\nThere might actually be a structural basis for its excellence as a student model…",
  "title": "Why Qwen is Dynamically Stable: An Empirical Phase Map of 10 LLMs"
}