github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 13:11:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4519] ollama run codellama:34b issue #2833

New Issue
Closed
opened 2026-04-12 13:10:27 -05:00 by GiteaMirror · 15 comments
GiteaMirror commented 2026-04-12 13:10:27 -05:00
Owner
Copy Link

Originally created by @Iliceth on GitHub (May 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4519

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Every model I tested with ollama runs fine, but when trying: ollama run codellama:34b, I get Error: llama runner process has terminated: signal: segmentation fault (core dumped)Tried the 13B-version then, works fine.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.37

Originally created by @Iliceth on GitHub (May 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4519 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Every model I tested with ollama runs fine, but when trying: `ollama run codellama:34b`, I get `Error: llama runner process has terminated: signal: segmentation fault (core dumped)`Tried the 13B-version then, works fine. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.37
GiteaMirror added the bug label 2026-04-12 13:10:27 -05:00
GiteaMirror commented 2026-04-12 13:10:28 -05:00
Author
Owner
Copy Link

@izzy84 commented on GitHub (May 19, 2024):

same here

<!-- gh-comment-id:2119304150 --> @izzy84 commented on GitHub (May 19, 2024): same here
GiteaMirror commented 2026-04-12 13:10:29 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 19, 2024):

So sorry about this, looking into why this is happening.

<!-- gh-comment-id:2119313281 --> @jmorganca commented on GitHub (May 19, 2024): So sorry about this, looking into why this is happening.
GiteaMirror commented 2026-04-12 13:10:29 -05:00
Author
Owner
Copy Link

@jonz-secops commented on GitHub (May 22, 2024):

same

<!-- gh-comment-id:2125799265 --> @jonz-secops commented on GitHub (May 22, 2024): same
GiteaMirror commented 2026-04-12 13:10:29 -05:00
Author
Owner
Copy Link

@barrard commented on GitHub (May 23, 2024):

I'm also getting this on 7b-python and 13b-python

<!-- gh-comment-id:2125989056 --> @barrard commented on GitHub (May 23, 2024): I'm also getting this on 7b-python and 13b-python
GiteaMirror commented 2026-04-12 13:10:29 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 23, 2024):

Could you share your server log, and your VRAM size? This is a larger model, so my suspicion is we're off on our memory prediction.

<!-- gh-comment-id:2127395463 --> @dhiltgen commented on GitHub (May 23, 2024): Could you share your server log, and your VRAM size? This is a larger model, so my suspicion is we're off on our memory prediction.
GiteaMirror commented 2026-04-12 13:10:30 -05:00
Author
Owner
Copy Link

@9SMTM6 commented on GitHub (May 23, 2024):

Same here.

AMD CPU in contrast to OP.

16 GB VRAM (RTX 4070 Ti Super)

Log attached.
codellama_crashdump_shortend.log

<!-- gh-comment-id:2127471937 --> @9SMTM6 commented on GitHub (May 23, 2024): Same here. AMD CPU in contrast to OP. 16 GB VRAM (RTX 4070 Ti Super) Log attached. [codellama_crashdump_shortend.log](https://github.com/ollama/ollama/files/15419278/codellama_crashdump_shortend.log)
GiteaMirror commented 2026-04-12 13:10:30 -05:00
Author
Owner
Copy Link

@jonz-secops commented on GitHub (May 23, 2024):

To add details ..

AMD 5950X on x570E
32 GB CPU RAM

6900XT
16GB VRAM

server log; doesn't appear to have the events in it anymore, but I'll try and recreate later today if I can.

<!-- gh-comment-id:2127546957 --> @jonz-secops commented on GitHub (May 23, 2024): To add details .. AMD 5950X on x570E 32 GB CPU RAM 6900XT 16GB VRAM server log; doesn't appear to have the events in it anymore, but I'll try and recreate later today if I can.
GiteaMirror commented 2026-04-12 13:10:30 -05:00
Author
Owner
Copy Link

@Iliceth commented on GitHub (May 23, 2024):

Hereby my log.

ollama_logs.txt

I can run mixtral and dolphin-mixtral fine and those are some big ones too.

Anyhow my current system is i7-9700K + 32 GB RAM + RTX 3090 with 24 GB VRAM

<!-- gh-comment-id:2127643839 --> @Iliceth commented on GitHub (May 23, 2024): Hereby my log. [ollama_logs.txt](https://github.com/ollama/ollama/files/15420085/ollama_logs.txt) I can run mixtral and dolphin-mixtral fine and those are some big ones too. Anyhow my current system is i7-9700K + 32 GB RAM + RTX 3090 with 24 GB VRAM
GiteaMirror commented 2026-04-12 13:10:30 -05:00
Author
Owner
Copy Link

@izzy84 commented on GitHub (May 23, 2024):

I7 7700K with 32gb ram and 6 GPUs with in total 51gb vram.

I can run all models, even llama3:70b without problems, which is already a big model. But I get error with codellama 34b

<!-- gh-comment-id:2127728123 --> @izzy84 commented on GitHub (May 23, 2024): I7 7700K with 32gb ram and 6 GPUs with in total 51gb vram. I can run all models, even llama3:70b without problems, which is already a big model. But I get error with codellama 34b
GiteaMirror commented 2026-04-12 13:10:31 -05:00
Author
Owner
Copy Link

@FukangSun commented on GitHub (May 24, 2024):

same here .I use 0.1.38 version of official docker image.
E5-2670 + 96gb ram + 1 RTX 4090 . also get below error when running codellama 34b :

ollama run codellama-34b-instruct:Q4_K_M
Error: llama runner process has terminated: signal: segmentation fault (core dumped)

Gentleman, I find another way, downgrade to 0.1.32 is okay to load codellama and large model. 0.1.33 - 0.1.39 I tested all not worked.

<!-- gh-comment-id:2129871789 --> @FukangSun commented on GitHub (May 24, 2024): same here .I use 0.1.38 version of official docker image. E5-2670 + 96gb ram + 1 RTX 4090 . also get below error when running codellama 34b : > ollama run codellama-34b-instruct:Q4_K_M Error: llama runner process has terminated: signal: segmentation fault (core dumped) # Gentleman, I find another way, downgrade to 0.1.32 is okay to load codellama and large model. 0.1.33 - 0.1.39 I tested all not worked.
GiteaMirror commented 2026-04-12 13:10:31 -05:00
Author
Owner
Copy Link

@AlexanderZhk commented on GitHub (May 26, 2024):

same. Phind-codellama from the repository works, loading gguf doesn't though

<!-- gh-comment-id:2132407079 --> @AlexanderZhk commented on GitHub (May 26, 2024): same. Phind-codellama from the repository works, loading gguf doesn't though
GiteaMirror commented 2026-04-12 13:10:31 -05:00
Author
Owner
Copy Link

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

Did upgrade to 0.1.41 in the meantime, but the problem persists.

<!-- gh-comment-id:2146887979 --> @Iliceth commented on GitHub (Jun 4, 2024): Did upgrade to 0.1.41 in the meantime, but the problem persists.
GiteaMirror commented 2026-04-12 13:10:32 -05:00
Author
Owner
Copy Link

@Iliceth commented on GitHub (Jun 14, 2024):

@jmorganca Is there any insight yet on what goes wrong? I upgraded to 0.1.44 today, but still no luck. The info @FukangSun provided might be helpful, in that the latest version without this issue seems to have been 0.1.32 for people who experience this problem.

<!-- gh-comment-id:2167939133 --> @Iliceth commented on GitHub (Jun 14, 2024): @jmorganca Is there any insight yet on what goes wrong? I upgraded to 0.1.44 today, but still no luck. The info @FukangSun provided might be helpful, in that the latest version without this issue seems to have been 0.1.32 for people who experience this problem.
GiteaMirror commented 2026-04-12 13:10:32 -05:00
Author
Owner
Copy Link

@Pomyk commented on GitHub (Jun 19, 2024):

I compiled from source and it works now.

<!-- gh-comment-id:2178858368 --> @Pomyk commented on GitHub (Jun 19, 2024): I compiled from source and it works now.
GiteaMirror commented 2026-04-12 13:10:33 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 19, 2024):

I've also confirmed that the latest llama.cpp bump has picked up a fix from upstream that resolves this in 0.1.45. (0.1.44 was still broken)

<!-- gh-comment-id:2179090164 --> @dhiltgen commented on GitHub (Jun 19, 2024): I've also confirmed that the latest llama.cpp bump has picked up a fix from upstream that resolves this in 0.1.45. (0.1.44 was still broken)
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#2833
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?