{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreib6wh6qib5nd456dhsknqdzzedipzaxay3smzlowjlu4kfhhtps7u",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mihorqqjabo2"
  },
  "path": "/t/failing-to-use-qwen3-5-397b-a17b-through-hf-inference/174868#post_1",
  "publishedAt": "2026-04-01T20:09:27.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Did something change about this model ? I used to have no issues running this model inside Zed Editor - but today for some reason I am getting error:\n\n\n     {\"status\":400,\"error\":\"BAD REQUEST\",\"message\":\"payload validation: max_completion_tokens is limited to 16384 for qwen3.5-397b-a17b\"}\n\n\nEven when I change the max_completion_tokens param to below that in Zed, it doesnt do anything - the error still happens.\nAnyone may have any idea whats going on?",
  "title": "Failing to use Qwen3.5-397B-A17B through HF inference"
}