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 #5950] Help to install the ollama files in my /home/myUser folder (install files, not the models). #65753

New Issue
Closed
opened 2026-05-03 22:32:58 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-03 22:32:58 -05:00
Owner
Copy Link

Originally created by @andrerclaudio on GitHub (Jul 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5950

Has anyone modified the script to install Ollama in a location other than the root folders? I want to change it to work only for my user using the install script for Linux. Can anyone help?

I changed it as follows:
asimov is the username.

...

BINDIR="/home/asimov/.local/bin"
mkdir -p $BINDIR
status "Installing ollama to $BINDIR..."
install -o $(id -u asimov) -g $(id -g asimov) -m 755 $TEMP_DIR/ollama $BINDIR/ollama

status 'The Ollama API is now available at 127.0.0.1:11434.'
status 'Install complete. Run "ollama" from the command line.'

configure_systemd() {
if ! id ollama >/dev/null 2>&1; then
status "Creating ollama user..."
sudo useradd -r -s /bin/false -U -m -d /home/asimov ollama
fi
if getent group render >/dev/null 2>&1; then
status "Adding ollama user to render group..."
sudo usermod -a -G render ollama
fi
if getent group video >/dev/null 2>&1; then
status "Adding ollama user to video group..."
sudo usermod -a -G video ollama
fi
status "Adding current user to ollama group..."
sudo usermod -a -G ollama $(whoami)
status "Creating ollama systemd service..."
sudo tee /etc/systemd/system/ollama.service > /dev/null <<EOF
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=$BINDIR/ollama serve
User=asimov
Group=asimov
Restart=always
RestartSec=3
Environment="PATH=$PATH"

[Install]
WantedBy=default.target

...

You guys see more to change?

Originally created by @andrerclaudio on GitHub (Jul 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5950 Has anyone modified the script to install Ollama in a location other than the root folders? I want to change it to work only for my user using the install script for Linux. Can anyone help? I changed it as follows: asimov is the username. ... BINDIR="/home/asimov/.local/bin" mkdir -p $BINDIR status "Installing ollama to $BINDIR..." install -o $(id -u asimov) -g $(id -g asimov) -m 755 $TEMP_DIR/ollama $BINDIR/ollama status 'The Ollama API is now available at 127.0.0.1:11434.' status 'Install complete. Run "ollama" from the command line.' configure_systemd() { if ! id ollama >/dev/null 2>&1; then status "Creating ollama user..." sudo useradd -r -s /bin/false -U -m -d /home/asimov ollama fi if getent group render >/dev/null 2>&1; then status "Adding ollama user to render group..." sudo usermod -a -G render ollama fi if getent group video >/dev/null 2>&1; then status "Adding ollama user to video group..." sudo usermod -a -G video ollama fi status "Adding current user to ollama group..." sudo usermod -a -G ollama $(whoami) status "Creating ollama systemd service..." sudo tee /etc/systemd/system/ollama.service > /dev/null <<EOF [Unit] Description=Ollama Service After=network-online.target [Service] ExecStart=$BINDIR/ollama serve User=asimov Group=asimov Restart=always RestartSec=3 Environment="PATH=$PATH" [Install] WantedBy=default.target ... You guys see more to change?
GiteaMirror commented 2026-05-03 22:32:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 25, 2024):

You can just get the binary:

$ curl -o ollama -L https://ollama.com/download/ollama-linux-amd64
$ chmod +x ollama

Start the server:

$ nohup ./ollama serve > ollama.log 2>&1 &

Interact with it:

$ ./ollama run llama3 "hello"
pulling manifest 
pulling 6a0746a1ec1a... 100% ▕██████████████████▏ 4.7 GB                         
pulling 4fa551d4f938... 100% ▕██████████████████▏  12 KB                         
pulling 8ab4849b038c... 100% ▕██████████████████▏  254 B                         
pulling 577073ffcc6c... 100% ▕██████████████████▏  110 B                         
pulling 3f8eb4da87fa... 100% ▕██████████████████▏  485 B                         
verifying sha256 digest 
writing manifest 
removing any unused layers 
success 
Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?

Models are in ~/.ollama, you change that by setting OLLAMA_MODELS and restarting the server.

<!-- gh-comment-id:2250326456 --> @rick-github commented on GitHub (Jul 25, 2024): You can just get the binary: ```sh $ curl -o ollama -L https://ollama.com/download/ollama-linux-amd64 $ chmod +x ollama ``` Start the server: ```sh $ nohup ./ollama serve > ollama.log 2>&1 & ``` Interact with it: ``` $ ./ollama run llama3 "hello" pulling manifest pulling 6a0746a1ec1a... 100% ▕██████████████████▏ 4.7 GB pulling 4fa551d4f938... 100% ▕██████████████████▏ 12 KB pulling 8ab4849b038c... 100% ▕██████████████████▏ 254 B pulling 577073ffcc6c... 100% ▕██████████████████▏ 110 B pulling 3f8eb4da87fa... 100% ▕██████████████████▏ 485 B verifying sha256 digest writing manifest removing any unused layers success Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat? ``` Models are in `~/.ollama`, you change that by setting `OLLAMA_MODELS` and restarting the server.
GiteaMirror commented 2026-05-03 22:32:59 -05:00
Author
Owner
Copy Link

@andrerclaudio commented on GitHub (Jul 25, 2024):

Hi, @rick-github.
Thanks for your reply.
It is a very good idea.

Right now, I have the variable OLLAMA_MODELS set in the ollama.service file, so I am saving the models in the folder I want.

But, assuming this is the first time I am going to install it using the method you mentioned, and I don't have the ollama.service file anymore, should the OLLAMA_MODELS variable be set in my .bashrc file?

<!-- gh-comment-id:2250445348 --> @andrerclaudio commented on GitHub (Jul 25, 2024): Hi, @rick-github. Thanks for your reply. It is a very good idea. Right now, I have the variable OLLAMA_MODELS set in the ollama.service file, so I am saving the models in the folder I want. But, assuming this is the first time I am going to install it using the method you mentioned, and I don't have the ollama.service file anymore, should the OLLAMA_MODELS variable be set in my .bashrc file?
GiteaMirror commented 2026-05-03 22:32:59 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 25, 2024):

Either in your .bashrc, or you can create a script to start the ollama server:

#!/bin/bash

export OLLAMA_MODELS=/some/random/dir
nohup ./ollama serve > ollama.log 2>&1 &
<!-- gh-comment-id:2250456176 --> @rick-github commented on GitHub (Jul 25, 2024): Either in your .bashrc, or you can create a script to start the ollama server: ```sh #!/bin/bash export OLLAMA_MODELS=/some/random/dir nohup ./ollama serve > ollama.log 2>&1 & ```
GiteaMirror commented 2026-05-03 22:32:59 -05:00
Author
Owner
Copy Link

@andrerclaudio commented on GitHub (Jul 25, 2024):

Got it.
Thanks @rick-github for your help.

<!-- gh-comment-id:2250493454 --> @andrerclaudio commented on GitHub (Jul 25, 2024): Got it. Thanks @rick-github for your help.
GiteaMirror commented 2026-05-03 22:33:00 -05:00
Author
Owner
Copy Link

@APMonitor commented on GitHub (Feb 2, 2025):

The binary is now available from:

curl -L https://ollama.com/download/ollama-linux-amd64.tgz -o ollama-linux-amd64.tgz
tar -xzf ollama-linux-amd64.tgz

I created an ollama folder. The tar file extracts to create a bin and lib file in your directory with the ollama binary in the bin folder. After chmod +x ./bin/ollama and creating a models folder in your /home/{usr}/ollama directory, start the ollama service:

#!/bin/bash

export OLLAMA_MODELS=/home/{usr}/ollama/models
nohup ./bin/ollama serve > ollama.log 2>&1 &

Run models with:

./bin/ollama run phi4

Here are the manual installation instructions.

<!-- gh-comment-id:2629201854 --> @APMonitor commented on GitHub (Feb 2, 2025): The binary is now available from: ```bash curl -L https://ollama.com/download/ollama-linux-amd64.tgz -o ollama-linux-amd64.tgz tar -xzf ollama-linux-amd64.tgz ``` I created an ollama folder. The tar file extracts to create a `bin` and `lib` file in your directory with the `ollama` binary in the bin folder. After `chmod +x ./bin/ollama` and creating a `models` folder in your `/home/{usr}/ollama` directory, start the ollama service: ```bash #!/bin/bash export OLLAMA_MODELS=/home/{usr}/ollama/models nohup ./bin/ollama serve > ollama.log 2>&1 & ``` Run models with: ```bash ./bin/ollama run phi4 ``` Here are the [manual installation instructions](https://github.com/ollama/ollama/blob/main/docs/linux.md).
GiteaMirror commented 2026-05-03 22:33:00 -05:00
Author
Owner
Copy Link

@RaphaelMouravieff commented on GitHub (Mar 6, 2025):

this work for me.

nohup ./bin/ollama serve > ollama.log 2>&1 &
./bin/ollama run llama3.2

the prompt are very fast on terminal (2sec).

but when using python :

from langchain_ollama import OllamaLLM
model = OllamaLLM(model="llama3.2")
result = model.invoke(input="hello world")
print(result)

the code work but it's not using the gpu (very slow like 1min).

someone can help for this ?

<!-- gh-comment-id:2702416019 --> @RaphaelMouravieff commented on GitHub (Mar 6, 2025): this work for me. ```shell nohup ./bin/ollama serve > ollama.log 2>&1 & ./bin/ollama run llama3.2 ``` the prompt are very fast on terminal (2sec). but when using python : ```python from langchain_ollama import OllamaLLM model = OllamaLLM(model="llama3.2") result = model.invoke(input="hello world") print(result) ``` the code work but it's not using the gpu (very slow like 1min). someone can help for this ?
GiteaMirror commented 2026-05-03 22:33:01 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 6, 2025):

Server logs may aid in debugging.

<!-- gh-comment-id:2702433128 --> @rick-github commented on GitHub (Mar 6, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging.
GiteaMirror commented 2026-05-03 22:33:02 -05:00
Author
Owner
Copy Link

@RaphaelMouravieff commented on GitHub (Mar 6, 2025):

this work for me.

nohup ./bin/ollama serve > ollama.log 2>&1 &
./bin/ollama run llama3.2
the prompt are very fast on terminal (2sec).

but when using python :

from langchain_ollama import OllamaLLM
model = OllamaLLM(model="llama3.2")
result = model.invoke(input="hello world")
print(result)
the code work but it's not using the gpu (very slow like 1min).

someone can help for this ?

Disabling the proxy resolved connectivity issues with Ollama because the proxy was intercepting local API requests (127.0.0.1:11434).

<!-- gh-comment-id:2702528031 --> @RaphaelMouravieff commented on GitHub (Mar 6, 2025): > this work for me. > > nohup ./bin/ollama serve > ollama.log 2>&1 & > ./bin/ollama run llama3.2 > the prompt are very fast on terminal (2sec). > > but when using python : > > from langchain_ollama import OllamaLLM > model = OllamaLLM(model="llama3.2") > result = model.invoke(input="hello world") > print(result) > the code work but it's not using the gpu (very slow like 1min). > > someone can help for this ? Disabling the proxy resolved connectivity issues with Ollama because the proxy was intercepting local API requests (`127.0.0.1:11434`).
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#65753
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?