{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreididmulqzt4kgsehp5iaqiv7qwsuylwadrsizg4jrtkwja7qleyh4",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mi4ybl7xonm2"
  },
  "path": "/t/500-internal-server-error-with-ollama/174735#post_1",
  "publishedAt": "2026-03-28T13:44:20.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "huggingface.co",
    "Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF · Hugging Face"
  ],
  "textContent": "Hey guys!\n\nI’m new here to HF and trying to utilize local LLMs in general. I have been playing around with Claude Code using Ollama. It’s been working fine but I just installed a second GPU so am wanting to play with more models. I’m new to using HF to download. I’m trying to run the following model in Ollama and ultimately Claude Code:\n\nhuggingface.co\n\n### Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF · Hugging Face\n\nWe’re on a journey to advance and democratize artificial intelligence through open source and open science.\n\nI used the command provided by the ‘use this model’ drop down to run Ollama and pull the manifest.\n\n`ollama run ``hf.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF:Q8_0`\n\nIt downloaded fine, and I can confirm the file is in the directory and named as the model is trying to call. However, I’m still getting this error when I try to launch Ollama with it.\n\n`Error loading model: 500 Internal Server Error: unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-9093fa002d4e64576b0724bd67010de8f87d5ec284fa71d8394fc47e2d9c65be`\n\nI’m on Ubuntu 24.04 and have two RTX 4090s so it shouldn’t be a size problem. Does anyone have any ideas on what to look for?\n\nThank you!",
  "title": "500 Internal Server Error with Ollama"
}