github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12268] Explore ways to optimize installation size #70216

New Issue
Open
opened 2026-05-04 20:40:43 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 20:40:43 -05:00
Owner
Copy Link

Originally created by @dhiltgen on GitHub (Sep 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12268

Originally assigned to: @dhiltgen on GitHub.

With the recent addition of CUDA v13 to enable new GPUs, the bundle and installer sizes for Linux and Windows have increased. We should explore options to optimize the size and/or layout of the bundles and improve the Linux and Windows installers to only install the components applicable to the GPU(s) present on the users system, and ideally only download those applicable components at install/upgrade time.

Originally created by @dhiltgen on GitHub (Sep 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12268 Originally assigned to: @dhiltgen on GitHub. With the recent addition of CUDA v13 to enable new GPUs, the bundle and installer sizes for Linux and Windows have increased. We should explore options to optimize the size and/or layout of the bundles and improve the Linux and Windows installers to only install the components applicable to the GPU(s) present on the users system, and ideally only download those applicable components at install/upgrade time.
GiteaMirror added the installfeature request labels 2026-05-04 20:40:43 -05:00
GiteaMirror commented 2026-05-04 20:40:57 -05:00
Author
Owner
Copy Link

@inforithmics commented on GitHub (Sep 30, 2025):

What about changing the compressed format from zip to 7z (7zip). I recompressed the ollama-windows-amd64.zip to ollama-windows-amd64.7z which reduced the size from 1.8 GB to 1.0GB.

<!-- gh-comment-id:3353110481 --> @inforithmics commented on GitHub (Sep 30, 2025): What about changing the compressed format from zip to 7z (7zip). I recompressed the ollama-windows-amd64.zip to ollama-windows-amd64.7z which reduced the size from 1.8 GB to 1.0GB.
GiteaMirror commented 2026-05-04 20:40:59 -05:00
Author
Owner
Copy Link

@zsyo commented on GitHub (Nov 1, 2025):

Can the basic version load my locally installed CUDA to switch to GPU operation?

<!-- gh-comment-id:3476158333 --> @zsyo commented on GitHub (Nov 1, 2025): Can the basic version load my locally installed CUDA to switch to GPU operation?
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 feature request install
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#70216
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?