[GH-ISSUE #9420] granite3.2-vision Error: llama runner process has terminated: GGML_ASSERT(ggml_can_mul_mat(a, b)) failed #6144

Closed
opened 2026-04-12 17:29:39 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @VistritPandey on GitHub (Feb 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9420

What is the issue?

When I run this command, ollama run granite3.2-vision

I am getting this error:

Relevant log output

Error: llama runner process has terminated: GGML_ASSERT(ggml_can_mul_mat(a, b)) failed

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.12

Originally created by @VistritPandey on GitHub (Feb 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9420 ### What is the issue? When I run this command, `ollama run granite3.2-vision` I am getting this error: ### Relevant log output ```shell Error: llama runner process has terminated: GGML_ASSERT(ggml_can_mul_mat(a, b)) failed ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.12
GiteaMirror added the bug label 2026-04-12 17:29:39 -05:00
Author
Owner

@scharada commented on GitHub (Feb 28, 2025):

same here

<!-- gh-comment-id:2691210053 --> @scharada commented on GitHub (Feb 28, 2025): same here
Author
Owner

@vimagick commented on GitHub (Feb 28, 2025):

Supported by v0.5.13-rc1
Are you using v0.5.12?

<!-- gh-comment-id:2691260994 --> @vimagick commented on GitHub (Feb 28, 2025): Supported by [v0.5.13-rc1](https://github.com/ollama/ollama/releases/tag/v0.5.13-rc1) Are you using v0.5.12?
Author
Owner

@VistritPandey commented on GitHub (Feb 28, 2025):

Yes, I was using v0.5.12 but worked with v0.5.13-rc1. Thanks!
Closing the issue

<!-- gh-comment-id:2691348183 --> @VistritPandey commented on GitHub (Feb 28, 2025): Yes, I was using `v0.5.12` but worked with `v0.5.13-rc1`. Thanks! Closing the issue
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#6144