[GH-ISSUE #707] 127.0.0.1:11434: bind: address already in use #46836

New Issue

GiteaMirror · 2026-04-28T00:43:53-05:00

GiteaMirror commented

2026-04-28 00:43:53 -05:00

Originally created by @Nivek92 on GitHub (Oct 5, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/707

When I run ollama serve I get

Error: listen tcp 127.0.0.1:11434: bind: address already in use

After checking what's running on the port with sudo lsof -i :11434

I see that ollama is already running

ollama 2233 ollama 3u IPv4 37563 0t0 TCP localhost:11434 (LISTEN)

I killed the process and ran the serve command again and got the same error. So it seems that it tries to start the server twice.

Originally created by @Nivek92 on GitHub (Oct 5, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/707 When I run `ollama serve` I get `Error: listen tcp 127.0.0.1:11434: bind: address already in use` After checking what's running on the port with `sudo lsof -i :11434` I see that ollama is already running `ollama 2233 ollama 3u IPv4 37563 0t0 TCP localhost:11434 (LISTEN)` I killed the process and ran the serve command again and got the same error. So it seems that it tries to start the server twice.

GiteaMirror added the question label 2026-04-28 00:43:54 -05:00

GiteaMirror closed this issue

2026-04-28 00:44:18 -05:00

GiteaMirror commented

2026-04-28 00:44:24 -05:00

@BruceMacD commented on GitHub (Oct 5, 2023):

Is this on Mac or Linux?

On Mac the app (running in the toolbar) will automatically restart the server when it stops. Exit the toolbar app to stop the server.

On Linux the Ollama server is added as a system service. To stop it you can run $ systemctl stop ollama.

@BruceMacD commented on GitHub (Oct 5, 2023): Is this on Mac or Linux? On Mac the app (running in the toolbar) will automatically restart the server when it stops. Exit the toolbar app to stop the server. On Linux the Ollama server is added as a system service. To stop it you can run `$ systemctl stop ollama`.

GiteaMirror commented

2026-04-28 00:44:26 -05:00

@xyproto commented on GitHub (Oct 6, 2023):

brew services restart ollama might also be helpful, if on macOS.

@xyproto commented on GitHub (Oct 6, 2023): `brew services restart ollama` might also be helpful, if on macOS.

GiteaMirror commented

2026-04-28 00:44:27 -05:00

@orpic commented on GitHub (Oct 8, 2023):

same happened with me but only after the initial install.
Running from next time after systemctl stop ollama , it worked fine.

@orpic commented on GitHub (Oct 8, 2023): same happened with me but only after the initial install. Running from next time after `systemctl stop ollama` , it worked fine.

GiteaMirror commented

2026-04-28 00:44:28 -05:00

@Nivek92 commented on GitHub (Oct 9, 2023):

yeah it's on Linux, Ubuntu specifically. It's not really a problem as the service is working but very confusing as it happens on the initial install, when you don't assume the service is already running, making you believe another service is blocking the port.

@Nivek92 commented on GitHub (Oct 9, 2023): yeah it's on Linux, Ubuntu specifically. It's not really a problem as the service is working but very confusing as it happens on the initial install, when you don't assume the service is already running, making you believe another service is blocking the port.

GiteaMirror commented

2026-04-28 00:44:31 -05:00

@Yadheedhya06 commented on GitHub (Oct 21, 2023):

https://github.com/jmorganca/ollama/pull/872

@Yadheedhya06 commented on GitHub (Oct 21, 2023): https://github.com/jmorganca/ollama/pull/872

GiteaMirror commented

2026-04-28 00:44:33 -05:00

@technovangelist commented on GitHub (Dec 4, 2023):

It looks like this issue was solved already as per the linked issue as well as Bruce's comment. I will go ahead and close it now. If you think there is anything we left out, reopen and we can address. Thanks for being part of this great community.

@technovangelist commented on GitHub (Dec 4, 2023): It looks like this issue was solved already as per the linked issue as well as Bruce's comment. I will go ahead and close it now. If you think there is anything we left out, reopen and we can address. Thanks for being part of this great community.

GiteaMirror commented

2026-04-28 00:44:35 -05:00

@ibehnam commented on GitHub (Dec 11, 2023):

I'm on macOS and still have the issue even after doing brew services restart ollama. I used to see ollama's icon in menu bar but not anymore.

@ibehnam commented on GitHub (Dec 11, 2023): I'm on macOS and still have the issue even after doing `brew services restart ollama`. I used to see ollama's icon in menu bar but not anymore.

GiteaMirror commented

2026-04-28 00:44:37 -05:00

@DoLife commented on GitHub (Dec 12, 2023):

I`m having the same isssue but Im on windows using the docker

@DoLife commented on GitHub (Dec 12, 2023): I`m having the same isssue but Im on windows using the docker

GiteaMirror commented

2026-04-28 00:44:39 -05:00

@xyproto commented on GitHub (Dec 12, 2023):

@ibehnam @DoLife Are you sure you are not running Ollama twice? Have you also tried checking with docker ps that Ollama is not already running within Docker?

@xyproto commented on GitHub (Dec 12, 2023): @ibehnam @DoLife Are you sure you are not running Ollama twice? Have you also tried checking with `docker ps` that Ollama is not already running within Docker?

GiteaMirror commented

2026-04-28 00:44:42 -05:00

@buts101 commented on GitHub (Dec 22, 2023):

disable firewalld or any other ip filtering

@buts101 commented on GitHub (Dec 22, 2023): disable firewalld or any other ip filtering

GiteaMirror commented

2026-04-28 00:44:45 -05:00

@ClaudeRobbinCR commented on GitHub (Dec 23, 2023):

@technovangelist Actually, I was just running it on WSL2 ubuntu 22.04, and it showed the same error.

@ClaudeRobbinCR commented on GitHub (Dec 23, 2023): @technovangelist Actually, I was just running it on WSL2 ubuntu 22.04, and it showed the same error.

GiteaMirror commented

2026-04-28 00:44:47 -05:00

@shivrajjadhav733 commented on GitHub (Jan 8, 2024):

OS - Apple M1 Pro chip

I tried to install ollama on machine. Installation was successful. I can see Ollama icon in menu bar at the top.

when I try to run model using command -

ollama run laama2
Or
ollama run mistral

I get attached error of operation timed out.

I tried to run - brew services restart ollama and I got error saying “ Error: Formula ‘ollama’ is not installed.

How do I fix the errors and run models using ollama?

@shivrajjadhav733 commented on GitHub (Jan 8, 2024): OS - Apple M1 Pro chip I tried to install ollama on machine. Installation was successful. I can see Ollama icon in menu bar at the top. when I try to run model using command - ollama run laama2 Or ollama run mistral I get attached error of operation timed out. ![BC48A4D0-AA86-41AA-B611-961467611449](https://github.com/jmorganca/ollama/assets/35407279/6532b007-2626-4f4a-87fc-499aa96e9d2f) I tried to run - brew services restart ollama and I got error saying “ Error: Formula ‘ollama’ is not installed. How do I fix the errors and run models using ollama?

GiteaMirror commented

2026-04-28 00:44:49 -05:00

@inteligenciamilgrau commented on GitHub (Feb 5, 2024):

For me it's is happening because ollama was already running

try:

systemctl status ollama

And you will get something like telling you it's running (active):

ollama.service - Ollama Service
Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled)
Active: active (running) since Mon 2024-02-05 08:33:09 -03; 25min ago
Main PID: 3525 (ollama)
Tasks: 51 (limit: 9459)
Memory: 4.6G
CGroup: /system.slice/ollama.service
└─3525 /usr/local/bin/ollama serve

To start/stop this service use:

systemctl stop ollama
systemctl start ollama

@inteligenciamilgrau commented on GitHub (Feb 5, 2024): For me it's is happening because ollama was already running try: `systemctl status ollama` And you will get something like telling you it's running (active): > ollama.service - Ollama Service > Loaded: loaded (/etc/systemd/system/ollama.service; enabled; vendor preset: enabled) > Active: active (running) since Mon 2024-02-05 08:33:09 -03; 25min ago > Main PID: 3525 (ollama) > Tasks: 51 (limit: 9459) > Memory: 4.6G > CGroup: /system.slice/ollama.service > └─3525 /usr/local/bin/ollama serve To start/stop this service use: `systemctl stop ollama` `systemctl start ollama`

GiteaMirror commented

2026-04-28 00:44:51 -05:00

@lovincyrus commented on GitHub (Feb 15, 2024):

If you're still encountering this on mac,

lsof -i :11434
kill <PID>

@lovincyrus commented on GitHub (Feb 15, 2024): If you're still encountering this on mac, ``` lsof -i :11434 kill <PID> ```

GiteaMirror commented

2026-04-28 00:44:54 -05:00

@HPUhushicheng commented on GitHub (Mar 19, 2024):

ubuntu/debian
sudo apt update
sudo apt install lsof
lsof -i :11434
kill <PID>
ollama serve

centos
sudo yum update
sudo yum install lsof
lsof -i :11434
kill <PID>
ollama serve

@HPUhushicheng commented on GitHub (Mar 19, 2024): ubuntu/debian `sudo apt update` `sudo apt install lsof` `lsof -i :11434` `kill <PID>` `ollama serve` centos `sudo yum update` `sudo yum install lsof` `lsof -i :11434` `kill <PID>` `ollama serve`

GiteaMirror commented

2026-04-28 00:44:56 -05:00

@abdurahmanadilovic commented on GitHub (Apr 1, 2024):

when I run lsof -i :11434 I get no results, but if I do ollama serve I still get the address already in use error

@abdurahmanadilovic commented on GitHub (Apr 1, 2024): when I run `lsof -i :11434` I get no results, but if I do `ollama serve` I still get the address already in use error

GiteaMirror commented

2026-04-28 00:44:59 -05:00

@DeepNeurons commented on GitHub (Apr 2, 2024):

i encountered the same issue on Ubuntu 20.04.5 LTS
solution : export OLLAMA_HOST=localhost:8888
source : here

@DeepNeurons commented on GitHub (Apr 2, 2024): i encountered the same issue on Ubuntu 20.04.5 LTS solution : export OLLAMA_HOST=localhost:8888 source : [here](https://pypi.org/project/ollamac/)

GiteaMirror commented

2026-04-28 00:45:04 -05:00

@Bayout commented on GitHub (Apr 3, 2024):

@DeepNeurons Thanks brother

@Bayout commented on GitHub (Apr 3, 2024): @DeepNeurons Thanks brother

GiteaMirror commented

2026-04-28 00:45:06 -05:00

@Tchez commented on GitHub (Apr 6, 2024):

When I run ollama serve I get

Error: listen tcp 127.0.0.1:11434: bind: address already in use

After checking what's running on the port with sudo lsof -i :11434

I see that ollama is already running

ollama 2233 ollama 3u IPv4 37563 0t0 TCP localhost:11434 (LISTEN)

I killed the process and ran the serve command again and got the same error. So it seems that it tries to start the server twice.

Try this:

 sudo systemctl stop ollama

I wasn't able to do it without 'sudo'

@Tchez commented on GitHub (Apr 6, 2024): > When I run `ollama serve` I get > > `Error: listen tcp 127.0.0.1:11434: bind: address already in use` > > After checking what's running on the port with `sudo lsof -i :11434` > > I see that ollama is already running > > `ollama 2233 ollama 3u IPv4 37563 0t0 TCP localhost:11434 (LISTEN)` > > I killed the process and ran the serve command again and got the same error. So it seems that it tries to start the server twice. Try this: ```bash sudo systemctl stop ollama ``` > I wasn't able to do it without 'sudo'

GiteaMirror commented

2026-04-28 00:45:08 -05:00

@svr123456789 commented on GitHub (Apr 18, 2024):

Look like need to add
Environment="OLLAMA_HOST=0.0.0.0:11434"
into /etc/systemd/system/ollama.service

@svr123456789 commented on GitHub (Apr 18, 2024): Look like need to add `Environment="OLLAMA_HOST=0.0.0.0:11434"` into /etc/systemd/system/ollama.service

GiteaMirror commented

2026-04-28 00:45:12 -05:00

@AmmariAbdelmounaim commented on GitHub (Apr 29, 2024):

Ran into a bit of a snag with WSL where I was still getting errors even after stopping ollama using systemctl stop ollama. Turns out the listener port was still active. Here's a quick fix I found that worked for me on Windows:

Fire up your Command Prompt as admin and run the following to grab the PID of the problematic port:netstat -aon | findstr :11434
With the PID in hand, kill the process: taskkill /F /PID <PID>
Make sure to replace with your actual process ID.
After that's done, just restart ollama: ollama serve

@AmmariAbdelmounaim commented on GitHub (Apr 29, 2024): Ran into a bit of a snag with WSL where I was still getting errors even after stopping ollama using `systemctl stop ollama`. Turns out the listener port was still active. Here's a quick fix I found that worked for me on Windows: Fire up your Command Prompt as admin and run the following to grab the PID of the problematic port:`netstat -aon | findstr :11434` With the PID in hand, kill the process: `taskkill /F /PID <PID>` Make sure to replace <PID> with your actual process ID. After that's done, just restart ollama: `ollama serve`

GiteaMirror commented

2026-04-28 00:45:15 -05:00

@Pathsis commented on GitHub (Apr 30, 2024):

when I run lsof -i :11434 I get no results, but if I do ollama serve I still get the address already in use error

I have the same problem.

@Pathsis commented on GitHub (Apr 30, 2024): > when I run `lsof -i :11434` I get no results, but if I do `ollama serve` I still get the address already in use error I have the same problem.

GiteaMirror commented

2026-04-28 00:45:18 -05:00

@Pathsis commented on GitHub (Apr 30, 2024):

Ran into a bit of a snag with WSL where I was still getting errors even after stopping ollama using systemctl stop ollama. Turns out the listener port was still active. Here's a quick fix I found that worked for me on Windows:

Fire up your Command Prompt as admin and run the following to grab the PID of the problematic port:netstat -aon | findstr :11434 With the PID in hand, kill the process: taskkill /F /PID <PID> Make sure to replace with your actual process ID. After that's done, just restart ollama: ollama serve

I killed all the pids to the point where running lsof -i :11434 gives no output, but running ollama serve still gives me this error.

@Pathsis commented on GitHub (Apr 30, 2024): > Ran into a bit of a snag with WSL where I was still getting errors even after stopping ollama using `systemctl stop ollama`. Turns out the listener port was still active. Here's a quick fix I found that worked for me on Windows: > > Fire up your Command Prompt as admin and run the following to grab the PID of the problematic port:`netstat -aon | findstr :11434` With the PID in hand, kill the process: `taskkill /F /PID <PID>` Make sure to replace with your actual process ID. After that's done, just restart ollama: `ollama serve` I killed all the pids to the point where running `lsof -i :11434 ` gives no output, but running `ollama serve` still gives me this error.

GiteaMirror commented

2026-04-28 00:45:24 -05:00

@BruceMacD commented on GitHub (May 1, 2024):

Hey all, not seeing ollama in the output of lsof could be a permissions issue. When you install ollama on linux via the install script it creates a service user for the background process. You may need to stop the process via systemctl in that case.

Here is some troubleshooting steps that will hopefully help:

Stop the background service: sudo systemctl stop ollama
Run lsof as sudo to rule out permissions issues: sudo lsof -i :11434

@BruceMacD commented on GitHub (May 1, 2024): Hey all, not seeing ollama in the output of `lsof` could be a permissions issue. When you install ollama on linux via the install script it creates a service user for the background process. You may need to stop the process via systemctl in that case. Here is some troubleshooting steps that will hopefully help: - Stop the background service: `sudo systemctl stop ollama` - Run `lsof` as sudo to rule out permissions issues: `sudo lsof -i :11434`

GiteaMirror commented

2026-04-28 00:45:26 -05:00

@RichardScottOZ commented on GitHub (May 9, 2024):

that has seemed to work thanks Bruce

@RichardScottOZ commented on GitHub (May 9, 2024): that has seemed to work thanks Bruce

GiteaMirror commented

2026-04-28 00:45:27 -05:00

@justingolden21 commented on GitHub (May 11, 2024):

Same problem here (win10)

I only run ollama through command prompt and it doesn't let me kill the process

@justingolden21 commented on GitHub (May 11, 2024): Same problem here (win10) ![image](https://github.com/ollama/ollama/assets/30274440/5b673cac-aec8-44aa-bc51-5326cb06d394) I only run ollama through command prompt and it doesn't let me kill the process ![image](https://github.com/ollama/ollama/assets/30274440/2b166fb3-3ee0-4c03-96b9-94c9e53d8a8f)

GiteaMirror commented

2026-04-28 00:45:28 -05:00

@fcalabrow commented on GitHub (May 23, 2024):

On Windows, make sure that Llama app is not already running. Hit the right click and then quit Llama, then run it from the terminal with ollama serve

@fcalabrow commented on GitHub (May 23, 2024): On Windows, make sure that Llama app is not already running. Hit the right click and then quit Llama, then run it from the terminal with `ollama serve` <img width="176" alt="image" src="https://github.com/ollama/ollama/assets/87214888/4b18497a-45a8-4edc-bade-84f51b393a86">

GiteaMirror commented

2026-04-28 00:45:28 -05:00

@paralyser commented on GitHub (Jun 7, 2024):

Fresh install.
System synology .
Installed with both docker and portainer.
Wiped/restarted/updated/reinstalled several times. Tried around 10 (8888,8778,11434,11535,11636,11433 etc.. )different ports, but every port gives the same error( with different ports).
Specified ports, ( OLLAMA_HOST=0.0.0.0:11434 ) to every port, changed 0.0.0.0 to 127.0.0.1 also. Same errors
Error: listen tcp 0.0.0.0:11434: bind: address already in use.
Have no idea how to fix it.

@paralyser commented on GitHub (Jun 7, 2024): Fresh install. System synology . Installed with both docker and portainer. Wiped/restarted/updated/reinstalled several times. Tried around 10 (8888,8778,11434,11535,11636,11433 etc.. )different ports, but every port gives the same error( with different ports). Specified ports, ( OLLAMA_HOST=0.0.0.0:11434 ) to every port, changed 0.0.0.0 to 127.0.0.1 also. Same errors Error: listen tcp 0.0.0.0:11434: bind: address already in use. Have no idea how to fix it.

GiteaMirror commented

2026-04-28 00:45:30 -05:00

@SebastianoF commented on GitHub (Jul 9, 2024):

On Mac first install was naughty for me.

Even with the app quitted (from the top bar), the port was in use and being re-created immediately after killing it with kill <PID>.

So:

I started again the ollama app again, double clicking on the applications list.
I quitted it again via the right click icon, and the problem solved itself (I also disabled the app running at startup from the system settings, for the next time).

Now the ollama CLI from terminal works as expected, with the app still quitted.

@SebastianoF commented on GitHub (Jul 9, 2024): On Mac first install was naughty for me. Even with the app quitted (from the top bar), the port was in use and being re-created immediately after killing it with `kill <PID>`. So: - I started again the ollama app again, double clicking on the applications list. - I quitted it again via the right click icon, and the problem solved itself (I also disabled the app running at startup from the system settings, for the next time). Now the ollama CLI from terminal works as expected, with the app still quitted.

GiteaMirror commented

2026-04-28 00:45:33 -05:00

@loveplay1983 commented on GitHub (Feb 20, 2025):

When I run ollama serve I get

Error: listen tcp 127.0.0.1:11434: bind: address already in use

After checking what's running on the port with sudo lsof -i :11434

I see that ollama is already running

ollama 2233 ollama 3u IPv4 37563 0t0 TCP localhost:11434 (LISTEN)

I killed the process and ran the serve command again and got the same error. So it seems that it tries to start the server twice.

On Ubuntu, Ollama is typically installed as a systemd service that starts automatically at system startup. This means the Ollama API server is already running in the background, so you generally don't need to run ollama serve manually. If you do, the system complains with "127.0.0.1:11434: bind: address already in use."

To solve the issue, we can define a custom port in the service file as we do above. However, commands like ollama list will complain after we set up a custom port since they are bound to the default 11434. We can explicitly export the environment variable OLLAMA_HOST and use the same port defined in the service file. For example, export OLLAMA_HOST=0.0.0.0:11450 # 11450 is the custom port defined in the service file. Then, the command ollama list will work again.

@loveplay1983 commented on GitHub (Feb 20, 2025): > When I run `ollama serve` I get > > `Error: listen tcp 127.0.0.1:11434: bind: address already in use` > > After checking what's running on the port with `sudo lsof -i :11434` > > I see that ollama is already running > > `ollama 2233 ollama 3u IPv4 37563 0t0 TCP localhost:11434 (LISTEN)` > > I killed the process and ran the serve command again and got the same error. So it seems that it tries to start the server twice. On Ubuntu, Ollama is typically installed as a systemd service that starts automatically at system startup. This means the Ollama API server is already running in the background, so you generally don't need to run ollama serve manually. If you do, the system complains with "127.0.0.1:11434: bind: address already in use." To solve the issue, we can define a custom port in the service file as we do above. However, commands like ollama list will complain after we set up a custom port since they are bound to the default 11434. We can explicitly export the environment variable OLLAMA_HOST and use the same port defined in the service file. For example, export OLLAMA_HOST=0.0.0.0:11450 # 11450 is the custom port defined in the service file. Then, the command ollama list will work again.

GiteaMirror commented

2026-04-28 00:45:40 -05:00

@Jaykumaran commented on GitHub (Feb 24, 2025):

For Ubuntu

Step 1. sudo nano /etc/systemd/system/ollama.service

Add Environment="OLLAMA_HOST=0.0.0.0:11434"

Step 2: source ~/.bashrc

Step 3: systemctl stop ollama

If an warning pops up like:
Warning: The unit file, source configuration file or drop-ins of ollama.service changed on disk. Run 'systemctl daemon-reload' to reload units.

Finally,

Step 4: systemctl daemon-reload

It should work now,

ollama serve

@Jaykumaran commented on GitHub (Feb 24, 2025): For **Ubuntu** Step 1. `sudo nano /etc/systemd/system/ollama.service` Add `Environment="OLLAMA_HOST=0.0.0.0:11434"` Step 2: `source ~/.bashrc` Step 3: `systemctl stop ollama` If an warning pops up like: `Warning: The unit file, source configuration file or drop-ins of ollama.service changed on disk. Run 'systemctl daemon-reload' to reload units.` Finally, Step 4: `systemctl daemon-reload` It should work now, `ollama serve`

GiteaMirror commented

2026-04-28 00:45:42 -05:00

@Haseeeb21 commented on GitHub (Mar 19, 2025):

For Ubuntu

Step 1. sudo nano /etc/systemd/system/ollama.service

Add Environment="OLLAMA_HOST=0.0.0.0:11434"

Step 2: source ~/.bashrc

Step 3: systemctl stop ollama

If an warning pops up like: Warning: The unit file, source configuration file or drop-ins of ollama.service changed on disk. Run 'systemctl daemon-reload' to reload units.

Finally,

Step 4: systemctl daemon-reload

It should work now,

ollama serve

Worked Thanks!

@Haseeeb21 commented on GitHub (Mar 19, 2025): > For **Ubuntu** > > Step 1. `sudo nano /etc/systemd/system/ollama.service` > > Add `Environment="OLLAMA_HOST=0.0.0.0:11434"` > > Step 2: `source ~/.bashrc` > > Step 3: `systemctl stop ollama` > > If an warning pops up like: `Warning: The unit file, source configuration file or drop-ins of ollama.service changed on disk. Run 'systemctl daemon-reload' to reload units.` > > Finally, > > Step 4: `systemctl daemon-reload` > > It should work now, > > `ollama serve` Worked Thanks!

GiteaMirror commented

2026-04-28 00:45:43 -05:00

@eniodev commented on GitHub (Aug 31, 2025):

this worked for me https://github.com/ollama/ollama/issues/2194

@eniodev commented on GitHub (Aug 31, 2025): this worked for me https://github.com/ollama/ollama/issues/2194

GiteaMirror commented

2026-04-28 00:45:45 -05:00

@ghost commented on GitHub (Nov 22, 2025):

This model is the best to work for Bittensor.com

@ghost commented on GitHub (Nov 22, 2025): This model is the best to work for Bittensor.com

Sign in to join this conversation.

Branches Tags

main

hoyyeva/anthropic-local-image-path

dhiltgen/ci

dhiltgen/llama-runner

parth-remove-claude-desktop-launch

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#46836