ollama - 💡(How to fix) Fix Title: Error running openbmb/minicpm-o4.5 — GGML_ASSERT unsupported minicpmv version [2 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#14744Fetched 2026-04-08 00:32:14
View on GitHub
Comments
2
Participants
2
Timeline
3
Reactions
0
Author
Participants
Timeline (top)
commented ×2closed ×1

Error Message

  • Error shown: 500 Internal Server Error: llama runner process has terminated: GGML_ASSERT(false && "unsupported minicpmv version") failed
  • UI error: 500 Internal Server Error: llama runner process has terminated: GGML_ASSERT(false && "unsupported minicpmv version") failed. :contentReference[oaicite:8]{index=8}
RAW_BUFFERClick to expand / collapse

Environment

  • Ollama version: 0.17.7
  • OS: Windows 11 (Windows/10.0.22631)
  • GPU: NVIDIA GeForce RTX 4070 Laptop GPU, driver 13.1, VRAM 8.0 GiB
  • Models path: default (note: earlier logs mention models path not accessible: C:\Users\admin.ollama\models but model was pulled)

What I did

  • ollama run openbmb/minicpm-o4.5

What happened

  • Error shown: 500 Internal Server Error: llama runner process has terminated: GGML_ASSERT(false && "unsupported minicpmv version") failed

Relevant server logs (excerpt):

  • server discovery and GPU match: inference compute ... Name=CUDA0 description="NVIDIA GeForce RTX 4070 Laptop GPU" libdirs=ollama,cuda_v13 driver=13.1 pci_id=0000:01:00.0 type=discrete total="8.0 GiB" available="5.5 GiB" (from server log). :contentReference[oaicite:7]{index=7}
  • UI error: 500 Internal Server Error: llama runner process has terminated: GGML_ASSERT(false && "unsupported minicpmv version") failed. :contentReference[oaicite:8]{index=8}

What I tried

  • Confirmed GPU visible to Ollama; tried upgrading Ollama.

Request

  • Please advise whether current Ollama release supports the minicpmv version used by openbmb/minicpm-o4.5, or whether there's a recommended Ollama build/flag to enable that support. Thanks.

extent analysis

Fix Plan

The fix involves updating Ollama to a version that supports the minicpmv version used by openbmb/minicpm-o4.5.

  • Check the Ollama documentation or GitHub page for the latest version and its supported models.
  • Update Ollama to the latest version using the installation instructions provided.
  • If the latest version still doesn't support minicpmv, consider using a different model that is supported by your current Ollama version.

Example Code

No code changes are required for this fix. However, you can verify the Ollama version and supported models using the following command:

ollama --version
ollama --help

Verification

After updating Ollama, run the openbmb/minicpm-o4.5 model again to verify that the fix worked:

ollama run openbmb/minicpm-o4.5

If the model runs without errors, the fix was successful.

Extra Tips

  • Always check the Ollama documentation and GitHub page for the latest information on supported models and versions.
  • Consider joining the Ollama community or forums to stay up-to-date with the latest developments and to get help with any issues you may encounter.

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 Title: Error running openbmb/minicpm-o4.5 — GGML_ASSERT unsupported minicpmv version [2 comments, 2 participants]