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 #8234] Standard Linux install includes CUDA libraries even if unused #51769

New Issue
Closed
opened 2026-04-28 20:55:27 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 20:55:27 -05:00
Owner
Copy Link

Originally created by @lamyergeier on GitHub (Dec 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8234

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

The install script command curl -fsSL https://ollama.com/install.sh | sh

downloads following files

$ tree
.
├── libcublas.so.11 -> libcublas.so.11.5.1.109
├── libcublas.so.11.5.1.109
├── libcublas.so.12 -> ./libcublas.so.12.4.5.8
├── libcublas.so.12.4.5.8
├── libcublasLt.so.11 -> libcublasLt.so.11.5.1.109
├── libcublasLt.so.11.5.1.109
├── libcublasLt.so.12 -> ./libcublasLt.so.12.4.5.8
├── libcublasLt.so.12.4.5.8
├── libcudart.so.11.0 -> libcudart.so.11.3.109
├── libcudart.so.11.3.109
├── libcudart.so.12 -> libcudart.so.12.4.127
├── libcudart.so.12.4.127
└── runners
    ├── cpu_avx
    │   └── ollama_llama_server
    ├── cpu_avx2
    │   └── ollama_llama_server
    ├── cuda_v11_avx
    │   ├── libggml_cuda_v11.so
    │   └── ollama_llama_server
    ├── cuda_v12_avx
    │   ├── libggml_cuda_v12.so
    │   └── ollama_llama_server
    └── rocm_avx
        ├── libggml_rocm.so
        └── ollama_llama_server

This includes massive downloads for CUDA:

$ command du -h
943M    ./runners/cuda_v11_avx
9.4M    ./runners/cpu_avx2
9.4M    ./runners/cpu_avx
440M    ./runners/rocm_avx
1.2G    ./runners/cuda_v12_avx
2.6G    ./runners
3.5G    .

image

Issue

Please do not download the excessive unnecessary files if the device does not have nvidia GPU.

OS

Linux

GPU

Intel

CPU

Intel

Ollama version

0.5.4

Originally created by @lamyergeier on GitHub (Dec 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8234 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? The install script command `curl -fsSL https://ollama.com/install.sh | sh` downloads following files ``` $ tree . ├── libcublas.so.11 -> libcublas.so.11.5.1.109 ├── libcublas.so.11.5.1.109 ├── libcublas.so.12 -> ./libcublas.so.12.4.5.8 ├── libcublas.so.12.4.5.8 ├── libcublasLt.so.11 -> libcublasLt.so.11.5.1.109 ├── libcublasLt.so.11.5.1.109 ├── libcublasLt.so.12 -> ./libcublasLt.so.12.4.5.8 ├── libcublasLt.so.12.4.5.8 ├── libcudart.so.11.0 -> libcudart.so.11.3.109 ├── libcudart.so.11.3.109 ├── libcudart.so.12 -> libcudart.so.12.4.127 ├── libcudart.so.12.4.127 └── runners ├── cpu_avx │ └── ollama_llama_server ├── cpu_avx2 │ └── ollama_llama_server ├── cuda_v11_avx │ ├── libggml_cuda_v11.so │ └── ollama_llama_server ├── cuda_v12_avx │ ├── libggml_cuda_v12.so │ └── ollama_llama_server └── rocm_avx ├── libggml_rocm.so └── ollama_llama_server ``` This includes massive downloads for CUDA: ``` bash $ command du -h 943M ./runners/cuda_v11_avx 9.4M ./runners/cpu_avx2 9.4M ./runners/cpu_avx 440M ./runners/rocm_avx 1.2G ./runners/cuda_v12_avx 2.6G ./runners 3.5G . ``` ![image](https://github.com/user-attachments/assets/01208b96-3660-4dae-82e7-8521de0c3a4d) # Issue Please do not download the excessive unnecessary files if the device does not have nvidia GPU. ### OS Linux ### GPU Intel ### CPU Intel ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-04-28 20:55:27 -05:00
GiteaMirror commented 2026-04-28 20:55:31 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 6, 2025):

Let's track this via the existing issue #6531 requesting a restructuring of our bundles to omit cuda in the main bundle and split out into a different artifact.

<!-- gh-comment-id:2573588813 --> @dhiltgen commented on GitHub (Jan 6, 2025): Let's track this via the existing issue #6531 requesting a restructuring of our bundles to omit cuda in the main bundle and split out into a different artifact.
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#51769
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?