[GH-ISSUE #16052] qwen3moe (qwen3:30b, qwen3-coder:30b) fails to load with OLLAMA_NUM_PARALLEL>=4 on DGX Spark — persists 0.21.0 → 0.23.2 #87906

Closed
opened 2026-05-10 06:34:11 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @trinitycc2021 on GitHub (May 8, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/16052

What is the issue?

tail -n +3 /tmp/upstream-issue-draft.md | xclip -selection clipboard

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @trinitycc2021 on GitHub (May 8, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/16052 ### What is the issue? tail -n +3 /tmp/upstream-issue-draft.md | xclip -selection clipboard ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-10 06:34:11 -05:00
Author
Owner

@rick-github commented on GitHub (May 8, 2026):

Missing details but I'm going take a guess and say https://github.com/ollama/ollama/issues/14116. If that's not the cause, server logs will aid in debugging.

<!-- gh-comment-id:4410512871 --> @rick-github commented on GitHub (May 8, 2026): Missing details but I'm going take a guess and say https://github.com/ollama/ollama/issues/14116. If that's not the cause, [server logs](https://docs.ollama.com/troubleshooting) will aid in debugging.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#87906