ollama - 💡(How to fix) Fix loaded kimi-k2.5:cloud but I was working with Claude [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#15667Fetched 2026-04-19 15:04:32
View on GitHub
Comments
1
Participants
2
Timeline
2
Reactions
0
Author
Timeline (top)
commented ×1labeled ×1
RAW_BUFFERClick to expand / collapse

What is the issue?

Hi,

I launched ollama on the powershell terminal in win11. Ollama proposes to run kimi-k2.5:cloud and I press enter. I type "hi Kimi" and the model replies it is Claude.

I had a lengthy conversation trying to find the problem, but I could not diagnose it. This is the final output of Claude for adding to the bug report:

Bug Report Details:

  • Model: kimi-k2.5:cloud (architecture shows kimi-k2, 1.04T params)
  • Issue: Model routes to Anthropic/Claude API instead of Moonshot AI/Kimi
  • Evidence: /show info confirms Kimi architecture, but responses identify as "Claude by Anthropic"
  • Empty Modelfile: /show modelfile returns nothing (cloud model)
  • Your location: Cloud connection to ollama.com

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

extent analysis

TL;DR

The issue may be resolved by checking the configuration or API endpoint used by ollama to connect to the Kimi model, as it appears to be routing to the Anthropic/Claude API instead.

Guidance

  • Verify the API endpoint or configuration used by ollama to connect to the Kimi model to ensure it is correct and not pointing to the Anthropic/Claude API.
  • Check the ollama documentation or support resources to see if there are any known issues or workarounds for this problem.
  • Try running the /show info and /show modelfile commands again to confirm the model architecture and configuration.
  • Consider reaching out to the ollama support team or community for further assistance, as they may have more information about the issue.

Notes

The lack of information about the ollama version, OS, GPU, and CPU makes it difficult to provide a more specific solution. Additionally, the empty log output does not provide any clues about the issue.

Recommendation

Apply workaround: Try to manually configure the API endpoint or model selection in ollama to point to the correct Kimi model, if possible. This may require checking the ollama documentation or support resources for more information.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

ollama - 💡(How to fix) Fix loaded kimi-k2.5:cloud but I was working with Claude [1 comments, 2 participants]