github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #942] A question on memory #46974

New Issue
Closed
opened 2026-04-28 02:24:03 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 02:24:03 -05:00
Owner
Copy Link

Originally created by @pexus on GitHub (Oct 28, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/942

Hello this is a question - with regards to the memory spec on running the OSS LLM - see below:

Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.

Is the reference to Memory requirement for GPU or the Main Memory (CPU) ? or a combination of GPU Memory and CPU Memory ?

Appreciate a clarity on this.

Thanks in advance.

Originally created by @pexus on GitHub (Oct 28, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/942 Hello this is a question - with regards to the memory spec on running the OSS LLM - see below: _Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models._ Is the reference to Memory requirement for GPU or the Main Memory (CPU) ? or a combination of GPU Memory and CPU Memory ? Appreciate a clarity on this. Thanks in advance.
GiteaMirror commented 2026-04-28 02:24:07 -05:00
Author
Owner
Copy Link

@pexus commented on GitHub (Oct 28, 2023):

I have 32 GB RAM and 12 GB GPU VRAM.
I can run all 7B models fine.
When I try to load any of the 13B models I get an error and runner exits with illegal instruction core dump.

Error: llama runner process has terminated

<!-- gh-comment-id:1783890078 --> @pexus commented on GitHub (Oct 28, 2023): I have 32 GB RAM and 12 GB GPU VRAM. I can run all 7B models fine. When I try to load any of the 13B models I get an error and runner exits with illegal instruction core dump. Error: llama runner process has terminated
GiteaMirror commented 2026-04-28 02:24:12 -05:00
Author
Owner
Copy Link

@pexus commented on GitHub (Oct 28, 2023):

I was able load the 13b llama2 by explicitly specifying ollama run llama2:13b. I presume if we don't qualify the parameter size, then it defaults to the largest model, hence the cause my error.

<!-- gh-comment-id:1783917335 --> @pexus commented on GitHub (Oct 28, 2023): I was able load the 13b llama2 by explicitly specifying ollama run llama2:13b. I presume if we don't qualify the parameter size, then it defaults to the largest model, hence the cause my error.
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
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#46974
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?