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 #9720] Loading of models into main memory limited to 1-3GB even from fast storage media #68409

New Issue
Open
opened 2026-05-04 13:51:21 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 13:51:21 -05:00
Owner
Copy Link

Originally created by @m-schenker on GitHub (Mar 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9720

What is the issue?

I am on a Fedora 41 system with a mdadm array that can be read at 14GB/s by a single thread or 22GB/s by multiple threads but ollama loads the models into main memory at a rate from about 1GB to 3GB per second. This is especially bothersome because loading larger models takes minutes. This is true for both native installation as well as the ollama container image run by podman.

Relevant log output

OS

Linux

GPU

Intel

CPU

AMD

Ollama version

0.6.0

Originally created by @m-schenker on GitHub (Mar 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9720 ### What is the issue? I am on a Fedora 41 system with a mdadm array that can be read at 14GB/s by a single thread or 22GB/s by multiple threads but ollama loads the models into main memory at a rate from about 1GB to 3GB per second. This is especially bothersome because loading larger models takes minutes. This is true for both native installation as well as the ollama container image run by podman. ### Relevant log output ```shell ``` ### OS Linux ### GPU Intel ### CPU AMD ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-05-04 13:51:21 -05:00
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#68409
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?