### Install Ollama via Script

Source: https://docs.ollama.com/linux

Use the official install script for a quick setup. This command can also be used to update existing installations.

```shell
curl -fsSL https://ollama.com/install.sh | sh
```

--------------------------------

### Install Ollama Libraries

Source: https://docs.ollama.com/cloud

Install the necessary client libraries for Python or JavaScript.

```bash
pip install ollama
```

```bash
npm i ollama
```

--------------------------------

### Manual Pi Installation and Configuration

Source: https://docs.ollama.com/integrations/pi

Steps for manual installation and setting up provider models and default settings.

```bash
npm install -g @earendil-works/pi-coding-agent
```

```json
{
  "providers": {
    "ollama": {
      "baseUrl": "http://localhost:11434/v1",
      "api": "openai-completions",
      "apiKey": "ollama",
      "models": [
        {
          "id": "qwen3-coder"
        }
      ]
    }
  }
}
```

```json
{
  "defaultProvider": "ollama",
  "defaultModel": "qwen3-coder"
}
```

--------------------------------

### Start and Verify Ollama

Source: https://docs.ollama.com/linux

Commands to launch the server and check the installed version.

```shell
ollama serve
```

```shell
ollama -v
```

--------------------------------

### Install OpenCode

Source: https://docs.ollama.com/integrations/opencode

Installation commands for different operating systems.

```shell
curl -fsSL https://opencode.ai/install | bash
```

```powershell
npm install -g opencode-ai
```

--------------------------------

### Hermes Setup Wizard Prompts

Source: https://docs.ollama.com/integrations/hermes

Interactive prompts displayed during the manual setup process.

```text
How would you like to set up Hermes?

 →  Quick setup — provider, model & messaging (recommended)
    Full setup — configure everything
```

```text
API base URL [e.g. https://api.example.com/v1]: http://127.0.0.1:11434/v1
```

```text
API key [optional]:
```

```text
Verified endpoint via http://127.0.0.1:11434/v1/models (1 model(s) visible)
  Detected model: kimi-k2.5:cloud
  Use this model? [Y/n]:
```

```text
Context length in tokens [leave blank for auto-detect]:
```

```text
Connect a messaging platform? (Telegram, Discord, etc.)

 →  Set up messaging now (recommended)
    Skip — set up later with 'hermes setup gateway'
```

```text
Launch hermes chat now? [Y/n]: Y
```

--------------------------------

### Install Ollama Python SDK

Source: https://docs.ollama.com/capabilities/tool-calling

Install the required package using pip or uv.

```bash
# with pip
pip install ollama -U

# with uv
uv add ollama
```

--------------------------------

### Quick Setup with Ollama

Source: https://docs.ollama.com/integrations/copilot-cli

Launch Copilot CLI with Ollama for a quick setup. This command initiates the Copilot CLI and connects it to the default Ollama model.

```shell
ollama launch copilot
```

--------------------------------

### Install Ollama JavaScript library

Source: https://docs.ollama.com/capabilities/tool-calling

Install the library using npm or bun.

```bash
# with npm
npm i ollama

# with bun
bun i ollama
```

--------------------------------

### Parameter usage examples

Source: https://docs.ollama.com/modelfile

Commonly used parameters and their syntax for configuration.

```text
num_ctx 4096
```

```text
repeat_last_n 64
```

```text
repeat_penalty 1.1
```

```text
temperature 0.7
```

```text
seed 42
```

```text
stop "AI assistant:"
```

--------------------------------

### Install Pi Extensions

Source: https://docs.ollama.com/integrations/pi

Commands to install additional capabilities via npm or git repositories.

```bash
pi install npm:@foo/some-tools
pi install git:github.com/user/repo@v1
```

```bash
pi install npm:@ollama/pi-web-search
```

```bash
pi install https://github.com/davebcn87/pi-autoresearch
```

--------------------------------

### Build from existing model

Source: https://docs.ollama.com/modelfile

Example of using an existing model as the base.

```text
FROM llama3.2
```

--------------------------------

### Install Copilot CLI (npm)

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI globally using npm on all platforms.

```shell
npm install -g @github/copilot
```

--------------------------------

### Launch OpenClaw

Source: https://docs.ollama.com/integrations/openclaw

Starts the OpenClaw gateway and TUI. Ollama handles installation and initial security configuration automatically.

```bash
ollama launch openclaw
```

--------------------------------

### Install Cline CLI

Source: https://docs.ollama.com/integrations/cline-cli

Install the Cline CLI globally using npm.

```bash
npm install -g cline
```

--------------------------------

### Install NemoClaw

Source: https://docs.ollama.com/integrations/nemoclaw

Run the installation script with environment variables configured for Ollama.

```bash
curl -fsSL https://www.nvidia.com/nemoclaw.sh | \
  NEMOCLAW_NON_INTERACTIVE=1 \
  NEMOCLAW_PROVIDER=ollama \
  NEMOCLAW_MODEL=nemotron-3-nano:30b \
  bash
```

--------------------------------

### Quick Setup Commands

Source: https://docs.ollama.com/integrations/codex

Commands for launching, configuring, and restoring the Codex CLI profile with Ollama.

```bash
ollama launch codex
```

```shell
ollama launch codex --config
```

```shell
ollama launch codex --restore
```

--------------------------------

### Install Copilot CLI (Windows WinGet)

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI on Windows using the WinGet package manager.

```powershell
winget install GitHub.Copilot
```

--------------------------------

### Install Codex CLI

Source: https://docs.ollama.com/integrations/codex

Install the Codex CLI globally using npm.

```bash
npm install -g @openai/codex
```

--------------------------------

### Tool Calling Example

Source: https://docs.ollama.com/api/anthropic-compatibility

Demonstrates how to use the Ollama API for tool calling with the 'get_weather' tool. Examples are provided in Python, JavaScript, and shell.

```APIDOC
## Tool Calling Example

This example demonstrates how to use the Ollama API for tool calling.

### Python Example
```python
import anthropic

client = anthropic.Anthropic(
    base_url='http://localhost:11434',
    api_key='ollama',
)

message = client.messages.create(
    model='qwen3-coder',
    max_tokens=1024,
    tools=[
        {
            'name': 'get_weather',
            'description': 'Get the current weather in a location',
            'input_schema': {
                'type': 'object',
                'properties': {
                    'location': {
                        'type': 'string',
                        'description': 'The city and state, e.g. San Francisco, CA'
                    }
                },
                'required': ['location']
            }
        }
    ],
    messages=[{'role': 'user', 'content': "What's the weather in San Francisco?"}]
)

for block in message.content:
    if block.type == 'tool_use':
        print(f'Tool: {block.name}')
        print(f'Input: {block.input}')
```

### JavaScript Example
```javascript
import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "http://localhost:11434",
  apiKey: "ollama",
});

const message = await anthropic.messages.create({
  model: "qwen3-coder",
  max_tokens: 1024,
  tools: [
    {
      name: "get_weather",
      description: "Get the current weather in a location",
      input_schema: {
        type: "object",
        properties: {
          location: {
            type: "string",
            description: "The city and state, e.g. San Francisco, CA",
          },
        },
        required: ["location"],
      },
    },
  ],
  messages: [{ role: "user", content: "What's the weather in San Francisco?" }],
});

for (const block of message.content) {
  if (block.type === "tool_use") {
    console.log("Tool:", block.name);
    console.log("Input:", block.input);
  }
}
```

### Shell Example
```shell
curl -X POST http://localhost:11434/v1/messages \
 -H "Content-Type: application/json" \
 -d 
'{ 
 "model": "qwen3-coder",
 "max_tokens": 1024,
 "tools": [
 {
 "name": "get_weather",
 "description": "Get the current weather in a location",
 "input_schema": {
 "type": "object",
 "properties": {
 "location": {
 "type": "string",
 "description": "The city and state"
 }
 },
 "required": ["location"]
 }
 }
 ],
 "messages": [{ "role": "user", "content": "What is the weather in San Francisco?" }]
}'
```
```

--------------------------------

### Install Droid CLI

Source: https://docs.ollama.com/integrations/droid

Use this command to install the Droid CLI on your system.

```bash
curl -fsSL https://app.factory.ai/cli | sh
```

--------------------------------

### Install Specific Version

Source: https://docs.ollama.com/linux

Use the OLLAMA_VERSION environment variable to install a specific release.

```shell
curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.5.7 sh
```

--------------------------------

### Install Copilot CLI (macOS / Linux Homebrew)

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI using Homebrew on macOS or Linux systems.

```shell
brew install copilot-cli
```

--------------------------------

### Generate with images

Source: https://docs.ollama.com/api/generate

Example of how to include images in the generate request.

```bash
curl http://localhost:11434/api/generate -d '{
  "model": "llava",
  "prompt": "what is in this image?",
  "images": ["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"],
  "stream": false
}'
```

--------------------------------

### Run and Configure OpenCode

Source: https://docs.ollama.com/integrations/opencode

Commands to start OpenCode or configure it without an interactive session.

```shell
opencode
```

```shell
ollama launch opencode --config
```

--------------------------------

### Launch Hermes Desktop

Source: https://docs.ollama.com/integrations/hermes-desktop

Initiates the automated installation and configuration flow for Hermes Desktop.

```bash
ollama launch hermes-desktop
```

--------------------------------

### Install Copilot CLI (macOS / Linux Script)

Source: https://docs.ollama.com/integrations/copilot-cli

Install Copilot CLI using a curl script on macOS or Linux.

```shell
curl -fsSL https://gh.io/copilot-install | bash
```

--------------------------------

### Launch OpenCode with Ollama

Source: https://docs.ollama.com/integrations/opencode

Starts the OpenCode agent using Ollama as the backend.

```shell
ollama launch opencode
```

--------------------------------

### Run a model

Source: https://docs.ollama.com/quickstart

Start a chat session with a specific model or a cloud-based variant.

```shell
ollama run gemma4
```

```shell
ollama run gemma4:cloud
```

--------------------------------

### Manage running models

Source: https://docs.ollama.com/cli

Commands to list, stop, and start the Ollama server.

```bash
ollama ps
```

```bash
ollama stop gemma4
```

```bash
ollama serve
```

--------------------------------

### Manual Pool Configuration

Source: https://docs.ollama.com/integrations/pool

Environment variable setup and direct execution commands for Pool.

```shell
export POOLSIDE_STANDALONE_BASE_URL=http://localhost:11434/v1
export POOLSIDE_API_KEY=ollama
```

```shell
pool -m kimi-k2.6:cloud
```

```shell
POOLSIDE_STANDALONE_BASE_URL=http://localhost:11434/v1 POOLSIDE_API_KEY=ollama pool -m kimi-k2.6:cloud
```

--------------------------------

### Configure Oh My Pi manually

Source: https://docs.ollama.com/integrations/oh-my-pi

Opens the configuration interface for OMP after manual installation.

```bash
ollama launch omp --config
```

--------------------------------

### Change Ollama installation directory

Source: https://docs.ollama.com/windows

Use this command to specify a custom installation path during the setup process.

```powershell
OllamaSetup.exe /DIR="d:\some\location"
```

--------------------------------

### Example conversation using MESSAGE

Source: https://docs.ollama.com/modelfile

A sequence of MESSAGE commands to guide model responses.

```text
MESSAGE user Is Toronto in Canada?
MESSAGE assistant yes
MESSAGE user Is Sacramento in Canada?
MESSAGE assistant no
MESSAGE user Is Ontario in Canada?
MESSAGE assistant yes
```

--------------------------------

### Configure Nvidia Container Toolkit (Apt)

Source: https://docs.ollama.com/docker

Sets up the Nvidia repository and installs the toolkit on Debian-based systems.

```shell
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
    | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -fsSL https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
    | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
    | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
```

```shell
sudo apt-get install -y nvidia-container-toolkit
```

--------------------------------

### Install and Run Marimo in a Sandbox

Source: https://docs.ollama.com/integrations/marimo

This command uses uv to execute the marimo editor within a sandboxed environment, ensuring a clean setup for notebook development.

```bash
uvx marimo edit --sandbox notebook.py
```

--------------------------------

### Install Hermes Agent Manually

Source: https://docs.ollama.com/integrations/hermes

Directly installs the Hermes Agent using the provided installation script.

```bash
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
```

--------------------------------

### Launch Oh My Pi with Ollama

Source: https://docs.ollama.com/integrations/oh-my-pi

Initializes OMP with Ollama as the provider and enables web search tools.

```bash
ollama launch omp
```

--------------------------------

### Define template and system instructions

Source: https://docs.ollama.com/modelfile

Examples of defining the prompt template, system instructions, and model metadata in a Modelfile.

```text
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""
```

```text
SYSTEM """<system message>"""
```

```text
ADAPTER <path to safetensor adapter>
```

```text
ADAPTER ./ollama-lora.gguf
```

```text
LICENSE """
<license text>
"""
```

--------------------------------

### Launch integrations

Source: https://docs.ollama.com/cli

Commands for configuring and launching external integrations.

```bash
ollama launch
```

```bash
ollama launch claude
```

```bash
ollama launch claude --model qwen3.5
```

```bash
ollama launch droid --config
```

--------------------------------

### Run cloud models

Source: https://docs.ollama.com/api/authentication

Execute a cloud-hosted model after signing in.

```shell
ollama run gpt-oss:120b-cloud
```

--------------------------------

### Install Claude Code

Source: https://docs.ollama.com/integrations/claude-code

Use these commands to install Claude Code on your respective operating system.

```shell
curl -fsSL https://claude.ai/install.sh | bash
```

```powershell
irm https://claude.ai/install.ps1 | iex
```

--------------------------------

### Create a model

Source: https://docs.ollama.com/openapi.yaml

Create a new model from an existing base model with custom system prompts or quantization settings.

```bash
curl http://localhost:11434/api/create -d '{ "from": "gemma4", "model": "alpaca", "system": "You are Alpaca, a helpful AI assistant. You only answer with Emojis." }'
```

```bash
curl http://localhost:11434/api/create -d '{ "model": "ollama", "from": "gemma4", "system": "You are Ollama the llama." }'
```

```bash
curl http://localhost:11434/api/create -d '{ "model": "llama3.1:8b-instruct-Q4_K_M", "from": "llama3.1:8b-instruct-fp16", "quantize": "q4_K_M" }'
```

--------------------------------

### Manual Copilot CLI Setup with Environment Variables

Source: https://docs.ollama.com/integrations/copilot-cli

Configure Copilot CLI to connect to Ollama using environment variables for the OpenAI-compatible API. Ensure Ollama is running and accessible.

```shell
export COPILOT_PROVIDER_BASE_URL=http://localhost:11434/v1
export COPILOT_PROVIDER_API_KEY=
export COPILOT_PROVIDER_WIRE_API=responses
export COPILOT_MODEL=qwen3.5
```

--------------------------------

### Define a custom Modelfile

Source: https://docs.ollama.com/modelfile

Example configuration for a custom model, including parameter adjustments and a system prompt.

```text
FROM llama3.2
# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.
```

--------------------------------

### Streaming Messages API Example

Source: https://docs.ollama.com/api/anthropic-compatibility

An example demonstrating how to stream message content using the Anthropic Messages API with Ollama.

```python
import anthropic

client = anthropic.Anthropic(
    base_url='http://localhost:11434',
    api_key='ollama',
)

with client.messages.stream(
    model='qwen3-coder',
    max_tokens=1024,
    messages=[{'role': 'user', 'content': 'Count from 1 to 10'}]
) as stream:
    for text in stream.text_stream:
        print(text, end='', flush=True)
```

```javascript
import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "http://localhost:11434",
  apiKey: "ollama",
});

const stream = await anthropic.messages.stream({
  model: "qwen3-coder",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Count from 1 to 10" }],
});

for await (const event of stream) {
  if (
    event.type === "content_block_delta" &&
    event.delta.type === "text_delta"
  ) {
    process.stdout.write(event.delta.text);
  }
}
```

```shell
curl -X POST http://localhost:11434/v1/messages \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-coder",
    "max_tokens": 1024,
    "stream": true,
    "messages": [{ "role": "user", "content": "Count from 1 to 10" }]
  }'
```

--------------------------------

### Run Copilot CLI After Manual Setup

Source: https://docs.ollama.com/integrations/copilot-cli

Execute Copilot CLI after setting the necessary environment variables for Ollama integration.

```shell
copilot
```

--------------------------------

### Configure Nvidia Container Toolkit (Yum/Dnf)

Source: https://docs.ollama.com/docker

Sets up the Nvidia repository and installs the toolkit on RHEL-based systems.

```shell
curl -fsSL https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo \
    | sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
```

```shell
sudo yum install -y nvidia-container-toolkit
```

--------------------------------

### Basic Messages API Example

Source: https://docs.ollama.com/api/anthropic-compatibility

A simple example demonstrating how to create a message using the Anthropic Messages API with Ollama.

```python
import anthropic

client = anthropic.Anthropic(
    base_url='http://localhost:11434',
    api_key='ollama',  # required but ignored
)

message = client.messages.create(
    model='qwen3-coder',
    max_tokens=1024,
    messages=[
        {'role': 'user', 'content': 'Hello, how are you?'}
    ]
)
print(message.content[0].text)
```

```javascript
import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "http://localhost:11434",
  apiKey: "ollama", // required but ignored
});

const message = await anthropic.messages.create({
  model: "qwen3-coder",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello, how are you?" }],
});

console.log(message.content[0].text);
```

```shell
curl -X POST http://localhost:11434/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: ollama" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "qwen3-coder",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Hello, how are you?" }]
  }'
```

--------------------------------

### Manual Setup Commands

Source: https://docs.ollama.com/integrations/codex

Commands to manually configure Codex to use Ollama with specific model flags.

```bash
codex --oss
```

```bash
codex --oss -m gpt-oss:120b
```

```bash
codex --oss -m gpt-oss:120b-cloud
```

--------------------------------

### Web Search JavaScript Library Example Output

Source: https://docs.ollama.com/capabilities/web-search

An example JSON output from the Ollama JavaScript library's web search function, displaying search results.

```json
{
  "results": [
    {
      "title": "Ollama",
      "url": "https://ollama.com/",
      "content": "Cloud models are now available..."
    },
    {
      "title": "What is Ollama? Introduction to the AI model management tool",
      "url": "https://www.hostinger.com/tutorials/what-is-ollama",
      "content": "Ollama is an open-source tool..."
    },
    {
      "title": "Ollama Explained: Transforming AI Accessibility and Language Processing",
      "url": "https://www.geeksforgeeks.org/artificial-intelligence/ollama-explained-transforming-ai-accessibility-and-language-processing/",
      "content": "Ollama is a groundbreaking..."
    }
  ]
}
```

--------------------------------

### Web Search Python Library Example Output

Source: https://docs.ollama.com/capabilities/web-search

An example output from the ollama Python library's web search function, showing a list of search results.

```python
results = [
    {
        "title": "Ollama",
        "url": "https://ollama.com/",
        "content": "Cloud models are now available in Ollama..."
    },
    {
        "title": "What is Ollama? Features, Pricing, and Use Cases - Walturn",
        "url": "https://www.walturn.com/insights/what-is-ollama-features-pricing-and-use-cases",
        "content": "Our services..."
    },
    {
        "title": "Complete Ollama Guide: Installation, Usage & Code Examples",
        "url": "https://collabnix.com/complete-ollama-guide-installation-usage-code-examples",
        "content": "Join our Discord Server..."
    }
]

```

--------------------------------

### Launch Hermes Desktop with a specific model

Source: https://docs.ollama.com/integrations/hermes-desktop

Starts Hermes Desktop directly with a pre-selected model.

```bash
ollama launch hermes-desktop --model <model>
```

--------------------------------

### Web Search API Response Example

Source: https://docs.ollama.com/capabilities/web-search

This is an example JSON response from the Ollama web search API, containing a list of relevant search results with titles, URLs, and content snippets.

```json
{
  "results": [
    {
      "title": "Ollama",
      "url": "https://ollama.com/",
      "content": "Cloud models are now available..."
    },
    {
      "title": "What is Ollama? Introduction to the AI model management tool",
      "url": "https://www.hostinger.com/tutorials/what-is-ollama",
      "content": "Ariffud M. 6min Read..."
    },
    {
      "title": "Ollama Explained: Transforming AI Accessibility and Language ...",
      "url": "https://www.geeksforgeeks.org/artificial-intelligence/ollama-explained-transforming-ai-accessibility-and-language-processing/",
      "content": "Data Science Data Science Projects Data Analysis..."
    }
  ]
}
```

--------------------------------

### Pull Qwen3 Model

Source: https://docs.ollama.com/capabilities/web-search

Download the Qwen3 4B model required for the search agent example.

```bash
ollama pull qwen3:4b
```

--------------------------------

### GET /v1/models

Source: https://docs.ollama.com/api/openai-compatibility

Lists the available models.

```APIDOC
## GET /v1/models

### Description
Lists the available models.

### Method
GET

### Endpoint
/v1/models
```

--------------------------------

### Sign in to Ollama

Source: https://docs.ollama.com/api/authentication

Initiate the authentication process from the local installation.

```shell
ollama signin
```

--------------------------------

### Example API Response with Usage Metrics

Source: https://docs.ollama.com/api/usage

A sample JSON response from the /api/generate endpoint showing performance metrics like total_duration and token counts.

```json
{
  "model": "gemma4",
  "created_at": "2025-10-17T23:14:07.414671Z",
  "response": "Hello! How can I help you today?",
  "done": true,
  "done_reason": "stop",
  "total_duration": 174560334,
  "load_duration": 101397084,
  "prompt_eval_count": 11,
  "prompt_eval_duration": 13074791,
  "eval_count": 18,
  "eval_duration": 52479709
}
```

--------------------------------

### GET /v1/models/{model}

Source: https://docs.ollama.com/api/openai-compatibility

Retrieves details for a specific model.

```APIDOC
## GET /v1/models/{model}

### Description
Retrieves details for a specific model.

### Method
GET

### Endpoint
/v1/models/{model}

### Parameters
#### Path Parameters
- **model** (string) - Required - The name of the model
```

--------------------------------

### Launch Cline with Ollama

Source: https://docs.ollama.com/integrations/cline-cli

Quickly launch Cline with Ollama as the provider or open the configuration menu.

```shell
ollama launch cline
```

```shell
ollama launch cline --config
```

--------------------------------

### Manually Install Ollama Binaries

Source: https://docs.ollama.com/linux

Download and extract the specific architecture package to /usr. Ensure old libraries are removed before upgrading.

```shell
curl -fsSL https://ollama.com/download/ollama-linux-amd64.tar.zst \
    | sudo tar x -C /usr
```

```shell
curl -fsSL https://ollama.com/download/ollama-linux-amd64-rocm.tar.zst \
    | sudo tar x -C /usr
```

```shell
curl -fsSL https://ollama.com/download/ollama-linux-arm64.tar.zst \
    | sudo tar x -C /usr
```