github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5674] Raspberry Pi no longer loading models #3540

New Issue
Closed
opened 2026-04-12 14:15:29 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:15:29 -05:00
Owner
Copy Link

Originally created by @bkev on GitHub (Jul 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5674

What is the issue?

Previously I've been able to run models such as Gemma and Internlm2 on the raspberry pi and they have worked. But, in later version of Ollama I'm now blocked from running them.

As far as I can tell, Ollama now checks RAM and doesn't load the model. Is there any override for this check? "Model requires more system memory than is available”.

I know it's limited on the pi but these models did work, if a little slow, and it would be nice to be able to continue to use them.

OS

Linux

GPU

No response

CPU

No response

Ollama version

0.2.3

Originally created by @bkev on GitHub (Jul 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5674 ### What is the issue? Previously I've been able to run models such as Gemma and Internlm2 on the raspberry pi and they have worked. But, in later version of Ollama I'm now blocked from running them. As far as I can tell, Ollama now checks RAM and doesn't load the model. Is there any override for this check? "Model requires more system memory than is available”. I know it's limited on the pi but these models did work, if a little slow, and it would be nice to be able to continue to use them. ### OS Linux ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.2.3
GiteaMirror added the bug label 2026-04-12 14:15:29 -05:00
GiteaMirror commented 2026-04-12 14:15:31 -05:00
Author
Owner
Copy Link

@bkev commented on GitHub (Jul 13, 2024):

So I can see this is due to a change in version 0.2.0

"Ollama will now return an error if the system does not have enough memory to run a model on Linux"

Is there an override for this (in the Ollama.service file for example)?

<!-- gh-comment-id:2226900406 --> @bkev commented on GitHub (Jul 13, 2024): So I can see this is due to a change in version 0.2.0 "Ollama will now return an error if the system does not have enough memory to run a model on Linux" Is there an override for this (in the Ollama.service file for example)?
GiteaMirror commented 2026-04-12 14:15:32 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 13, 2024):

I think the problem is this line:

22c5451fc2/llm/server.go (L130)

Because of the min, ollama will never load a model larger than the amount of RAM installed in the system, irrespective of how much swap is added. With resource constrained platforms like the Pi, this prevents loading even moderately useful models.

<!-- gh-comment-id:2226949671 --> @rick-github commented on GitHub (Jul 13, 2024): I think the problem is this line: https://github.com/ollama/ollama/blob/22c5451fc28b20dd83a389c49d9caf6a1e50a9e3/llm/server.go#L130 Because of the `min`, ollama will never load a model larger than the amount of RAM installed in the system, irrespective of how much swap is added. With resource constrained platforms like the Pi, this prevents loading even moderately useful models.
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#3540
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?