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 #9191] make ollama of windows amd64 version smaller #52501

New Issue
Open
opened 2026-04-28 23:31:06 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 23:31:06 -05:00
Owner
Copy Link

Originally created by @zmldndx on GitHub (Feb 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9191

The size of ggml-cuda.dll is more than twice larger than llama.cpp, can we make ollama-windows-amd64.zip much more smaller?
Our tool is based on ollama command line exe, and we want introduce users to download ollama automatically. but it's too big on windows, thus many people stop downloading.

Originally created by @zmldndx on GitHub (Feb 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9191 The size of ggml-cuda.dll is more than twice larger than llama.cpp, can we make ollama-windows-amd64.zip much more smaller? Our tool is based on ollama command line exe, and we want introduce users to download ollama automatically. but it's too big on windows, thus many people stop downloading.
GiteaMirror added the feature request label 2026-04-28 23:31:06 -05:00
GiteaMirror commented 2026-04-28 23:32:22 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Feb 18, 2025):

The release build of ollama for linux and windows builds for a wide set of CUDA and ROCm architectures. These represent a large proportion part of the artifact's size.

I have some idea on how to shrink the download size while maintaining broad compatibility but there's currently no bandwidth to work on this

For the time being, if file sizes are an issue, you can always build from source which will only build the architectures you specify

<!-- gh-comment-id:2667170325 --> @mxyng commented on GitHub (Feb 18, 2025): The release build of ollama for linux and windows builds for a wide set of CUDA and ROCm architectures. These represent a large proportion part of the artifact's size. I have some idea on how to shrink the download size while maintaining broad compatibility but there's currently no bandwidth to work on this For the time being, if file sizes are an issue, you can always build from source which will only build the architectures you specify
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
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#52501
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?