[GH-ISSUE #10909] Ollama - deepseek-r1:latest - EOF Error During Prediction #53687

Closed
opened 2026-04-29 04:30:09 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @savg92 on GitHub (May 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10909

Originally assigned to: @jmorganca on GitHub.

What is the issue?

I’m encountering an "EOF (EOF)" error when running a prediction with the
deepseek-r1:latest model in Ollama on my MacBook Pro M3.

Steps to Reproduce:

  1. Start Ollama: ollama start
  2. Run the following command: ollama run deepseek-r1:latest --verbose
  3. The command should attempt to run the deepseek-r1 model.

Expected Result:

The deepseek-r1 model should start running, and the --verbose flag
should provide detailed output during the prediction process.

Actual Result:

I receive the following error:

Error: POST predict: Post "http://127.0.0.1:49570/completion": EOF

Environment:

  • Ollama Version: 0.9.0
  • OS: macOS 15.5
  • Hardware: MacBook Pro M3

Additional Information:

  • I have tried restarting computer and Ollama and re-running the command, but the
    error persists.
  • I am using the latest version of Ollama 0.9.0

Relevant log output

Error: POST predict: Post "http://127.0.0.1:49570/completion": EOF

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @savg92 on GitHub (May 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10909 Originally assigned to: @jmorganca on GitHub. ### What is the issue? I’m encountering an "EOF (EOF)" error when running a prediction with the `deepseek-r1:latest` model in Ollama on my MacBook Pro M3. **Steps to Reproduce:** 1. Start Ollama: `ollama start` 2. Run the following command: `ollama run deepseek-r1:latest --verbose` 3. The command should attempt to run the `deepseek-r1` model. **Expected Result:** The `deepseek-r1` model should start running, and the `--verbose` flag should provide detailed output during the prediction process. **Actual Result:** I receive the following error: ``` Error: POST predict: Post "http://127.0.0.1:49570/completion": EOF ``` **Environment:** * **Ollama Version:** 0.9.0 * **OS:** macOS 15.5 * **Hardware:** MacBook Pro M3 **Additional Information:** * I have tried restarting computer and Ollama and re-running the command, but the error persists. * I am using the latest version of Ollama 0.9.0 ### Relevant log output ```shell Error: POST predict: Post "http://127.0.0.1:49570/completion": EOF ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 04:30:09 -05:00
Author
Owner

@jmorganca commented on GitHub (May 30, 2025):

Hi @savg92 sorry this happened. Do you have the logs handy? https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues

<!-- gh-comment-id:2921174438 --> @jmorganca commented on GitHub (May 30, 2025): Hi @savg92 sorry this happened. Do you have the logs handy? https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#53687