Getting "fetch failed" or "connection error" when trying to get a response from most models

#718
by auerovkh - opened

Effected models below:

"Fetch failed":

  • meta-llama/Llama-3.3-70B-Instruct
  • Qwen/Qwen2.5-72B-Instruct
  • CohereForAI/c4ai-command-r-plus-08-2024
  • NousResearch/Hermes-3-Llama-3.1-8B

"Connection error":

  • Qwen/Qwen3-235B-A22B
  • deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
  • nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Seem to be ok:

  • google/gemma-3-27b-it
  • mistralai/Mistral-Small-3.1-24B-Instruct-2503
  • Qwen/Qwen2.5-VL-32B-Instruct
  • microsoft/Phi-4

Qwen/QwQ-32B showed it's 'thinking'/reasoning, but then errored with "network error".

Hugging Chat org

Should be working again! Sorry for the issue.

@nsarrazin thanks! although the error's now changed to "Server response contains error: 404", which seems to be affecting the "Fetch failed" models listed.

Hugging Chat org

Seems like the issue is mainly with the command R+ model. Reported it internally

Seems to be resolved so closing. Thanks!

auerovkh changed discussion status to closed

Sign up or log in to comment