What causes "Ollama can't bind port 11434 — already in use"?

Ollama defaults to port 11434. Conflicts happen when: - Another Ollama instance is already running (systemd + manual start) - LM Studio's local server is running on the same port (rare, but happens) - A previous Ollama crashed without releasing the port - A Docker container has the port published

Network / downloads

Ollama can't bind port 11434 — already in use

Q: How do you fix "Ollama can't bind port 11434 — already in use"?

**1. Find what's holding the port:** ```bash # Linux / macOS lsof -i :11434 # or ss -tulpn | grep 11434 # Windows (PowerShell) Get-NetTCPConnection -LocalPort 11434 ``` **2. If it's an old Ollama process, kill it cleanly:** ```bash # Linux: stop the systemd service sudo systemctl stop ollama # macOS: kill the LaunchAgent launchctl bootout gui/$(id -u) /Library/LaunchAgents/com.ollama.ollama.plist 2>/dev/null pkill -f ollama # Then restart ollama serve ``` **3. Or run on a different port:** ```bash OLLAMA_HOST=0.0.0.0:11435 ollama serve ``` **4. If it's Docker:** ```bash docker ps | grep 11434 docker stop ``` **5. Production deployment:** prefer running Ollama as a systemd service with environment file pinning host + port. See the [Linux local AI guide](/systems/linux-local-ai).

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

By Fredoline Eruo · Last verified May 7, 2026

Cause

Ollama defaults to port 11434. Conflicts happen when:

Another Ollama instance is already running (systemd + manual start)
LM Studio's local server is running on the same port (rare, but happens)
A previous Ollama crashed without releasing the port
A Docker container has the port published

Solution

1. Find what's holding the port:

# Linux / macOS
lsof -i :11434
# or
ss -tulpn | grep 11434

# Windows (PowerShell)
Get-NetTCPConnection -LocalPort 11434

2. If it's an old Ollama process, kill it cleanly:

# Linux: stop the systemd service
sudo systemctl stop ollama

# macOS: kill the LaunchAgent
launchctl bootout gui/$(id -u) /Library/LaunchAgents/com.ollama.ollama.plist 2>/dev/null
pkill -f ollama

# Then restart
ollama serve

3. Or run on a different port:

OLLAMA_HOST=0.0.0.0:11435 ollama serve

4. If it's Docker:

docker ps | grep 11434
docker stop <container>

5. Production deployment: prefer running Ollama as a systemd service with environment file pinning host + port. See the Linux local AI guide.

Related errors

Did this fix it?

If your case was different, email support@runlocalai.co with what you saw and we'll update the page. If it worked but took different commands on your platform, we want to know that too.