github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4675] phi3: Error: llama runner process has terminated: exit status 0xc0000409 #2940

New Issue
Closed
opened 2026-04-12 13:18:43 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 13:18:43 -05:00
Owner
Copy Link

Originally created by @FreemanFeng on GitHub (May 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4675

What is the issue?

ollama run phi3:medium-128k
ollama run phi3:3.8-mini-128k-instruct-q4_0

above two models will cause issue
Error: llama runner process has terminated: exit status 0xc0000409

OS

Windows

GPU

Other

CPU

Intel

Ollama version

0.1.38

Originally created by @FreemanFeng on GitHub (May 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4675 ### What is the issue? ollama run phi3:medium-128k ollama run phi3:3.8-mini-128k-instruct-q4_0 above two models will cause issue Error: llama runner process has terminated: exit status 0xc0000409 ### OS Windows ### GPU Other ### CPU Intel ### Ollama version 0.1.38
GiteaMirror added the bug label 2026-04-12 13:18:43 -05:00
GiteaMirror commented 2026-04-12 13:18:44 -05:00
Author
Owner
Copy Link

@SleeplessBegonia commented on GitHub (May 28, 2024):

mee too

<!-- gh-comment-id:2134658854 --> @SleeplessBegonia commented on GitHub (May 28, 2024): mee too
GiteaMirror commented 2026-04-12 13:18:46 -05:00
Author
Owner
Copy Link

@timfpark commented on GitHub (May 28, 2024):

Also seeing something simliar with Apple M1 Max with Sonoma 14.5:

❯ ollama run phi3:14b-medium-128k-instruct-q4_0
Error: llama runner process has terminated: signal: abort trap error:done_getting_tensors: wrong number of tensors; expected 245, got 243

<!-- gh-comment-id:2136234480 --> @timfpark commented on GitHub (May 28, 2024): Also seeing something simliar with Apple M1 Max with Sonoma 14.5: ❯ ollama run phi3:14b-medium-128k-instruct-q4_0 Error: llama runner process has terminated: signal: abort trap error:done_getting_tensors: wrong number of tensors; expected 245, got 243
GiteaMirror commented 2026-04-12 13:18:46 -05:00
Author
Owner
Copy Link

@leuchtetgruen commented on GitHub (Jun 2, 2024):

Same here

<!-- gh-comment-id:2143978336 --> @leuchtetgruen commented on GitHub (Jun 2, 2024): Same here
GiteaMirror commented 2026-04-12 13:18:47 -05:00
Author
Owner
Copy Link

@akhilsbehl commented on GitHub (Jun 3, 2024):

I'm seeing the same error. Looking at journalctl, it says 'phi3' is not a recognised model name. Which is an issue that has been seen before. Funnily enough, phi3 mini was working earlier and had model family name as llama but that has also stopped working now.

<!-- gh-comment-id:2145243361 --> @akhilsbehl commented on GitHub (Jun 3, 2024): I'm seeing the same error. Looking at journalctl, it says 'phi3' is not a recognised model name. Which is an issue that has been seen before. Funnily enough, phi3 mini was working earlier and had model family name as llama but that has also stopped working now.
GiteaMirror commented 2026-04-12 13:18:47 -05:00
Author
Owner
Copy Link

@akhilsbehl commented on GitHub (Jun 3, 2024):

Also, I've been seeing this issue with 1.38, 1.39, and 1.41 as of today.

<!-- gh-comment-id:2145247869 --> @akhilsbehl commented on GitHub (Jun 3, 2024): Also, I've been seeing this issue with 1.38, 1.39, and 1.41 as of today.
GiteaMirror commented 2026-04-12 13:18:48 -05:00
Author
Owner
Copy Link

@hujunyao commented on GitHub (Jun 4, 2024):

I got same error when ollama run hhao/openbmb-minicpm-llama3-v-2_5:latest, ollama version is 1.41, windows version

<!-- gh-comment-id:2146476009 --> @hujunyao commented on GitHub (Jun 4, 2024): I got same error when ollama run hhao/openbmb-minicpm-llama3-v-2_5:latest, ollama version is 1.41, windows version
GiteaMirror commented 2026-04-12 13:18:49 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jun 9, 2024):

Hi there, this should be fixed in the latest version of Ollama: https://ollama.com/download

@hujunyao RE Minicpm - will track that here: https://github.com/ollama/ollama/issues/4900

Thanks for the issue!

<!-- gh-comment-id:2156704213 --> @jmorganca commented on GitHub (Jun 9, 2024): Hi there, this should be fixed in the latest version of Ollama: https://ollama.com/download @hujunyao RE Minicpm - will track that here: https://github.com/ollama/ollama/issues/4900 Thanks for the issue!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2940
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?