Get up and running with Llama 3, Mistral, Gemma, and other large language models.by adding more amd gpu support.
See the code
Start building with open models.
curl -fsSL https://ollama.com/install.sh | sh
irm https://ollama.com/install.ps1 | iex
For AMD use or build , please follow the guide on wiki
official support list
"gfx900" "gfx940" "gfx941" "gfx942" "gfx1010""gfx1012" "gfx1030" "gfx1100""gfx1101" "gfx1102"
Please download from ollama official
Example extra list add on this repo.
(ROCm5) "gfx803" "gfx900:xnack-" "gfx902" (ROCm6) gfx906:xnack- "gfx1010:xnack-" "gfx1011" "gfx1012:xnack-" "gfx1031" "gfx1032" "gfx1034" "gfx1035" "gfx1036" "gfx1103" "gfx1150" "gfx1201" (expertimental)"...
Please follow the wiki guide to build or use the pre-release version.
Note: gfx803: Reported as partially functional in HIP SDK 5.7 using the wiki method, but disabled in HIP SDK 6.1.2.
Note: gfx90c (with xnack-): Reported as partially functional in HIP SDK 5.7, with some testers experiencing partial success while others encountered issues in recent update. removed from support lists. Explore its through self-build as guided on the wiki.
curl -fsSL https://ollama.com/install.sh | sh
Configuring Environment Variables Tip For Unsupport GPUs
The official Ollama Docker image ollama/ollama is available on Docker Hub.
ollama
You'll be prompted to run a model or connect Ollama to your existing agents or applications such as Claude Code, OpenClaw, OpenCode , Codex, Copilot, and more.
To launch a specific integration:
ollama launch claude
Supported integrations include Claude Code, Codex, Copilot CLI, DeepSeek Harness, Droid, and OpenCode.
Use OpenClaw to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more:
ollama launch openclaw
Run and chat with Gemma 4:
ollama run gemma4
See ollama.com/library for the full list.
See the quickstart guide for more details.
Ollama has a REST API for running and managing models.
curl http://localhost:11434/api/chat -d '{
"model": "gemma4",
"messages": [{
"role": "user",
"content": "Why is the sky blue?"
}],
"stream": false
}'
See the API documentation for all endpoints.
pip install ollama
from ollama import chat
response = chat(model='gemma4', messages=[
{
'role': 'user',
'content': 'Why is the sky blue?',
},
])
print(response.message.content)
npm i ollama
import ollama from "ollama";
const response = await ollama.chat({
model: "gemma4",
messages: [{ role: "user", content: "Why is the sky blue?" }],
});
console.log(response.message.content);
Want to add your project? Open a pull request.
SwiftChat, Enchanted, Maid, Ollama App, Reins, and ConfiChat listed above also support mobile platforms.
345 followers · starred Sep 2025
2,248 followers · starred May 2025
413 followers · starred Feb 2025
22 followers · starred Feb 2025
Get up and running with Llama 3, Mistral, Gemma, and other large language models.by adding more amd gpu support.
See the code
Start building with open models.
curl -fsSL https://ollama.com/install.sh | sh
irm https://ollama.com/install.ps1 | iex
For AMD use or build , please follow the guide on wiki
official support list
"gfx900" "gfx940" "gfx941" "gfx942" "gfx1010""gfx1012" "gfx1030" "gfx1100""gfx1101" "gfx1102"
Please download from ollama official
Example extra list add on this repo.
(ROCm5) "gfx803" "gfx900:xnack-" "gfx902" (ROCm6) gfx906:xnack- "gfx1010:xnack-" "gfx1011" "gfx1012:xnack-" "gfx1031" "gfx1032" "gfx1034" "gfx1035" "gfx1036" "gfx1103" "gfx1150" "gfx1201" (expertimental)"...
Please follow the wiki guide to build or use the pre-release version.
Note: gfx803: Reported as partially functional in HIP SDK 5.7 using the wiki method, but disabled in HIP SDK 6.1.2.
Note: gfx90c (with xnack-): Reported as partially functional in HIP SDK 5.7, with some testers experiencing partial success while others encountered issues in recent update. removed from support lists. Explore its through self-build as guided on the wiki.
curl -fsSL https://ollama.com/install.sh | sh
Configuring Environment Variables Tip For Unsupport GPUs
The official Ollama Docker image ollama/ollama is available on Docker Hub.
ollama
You'll be prompted to run a model or connect Ollama to your existing agents or applications such as Claude Code, OpenClaw, OpenCode , Codex, Copilot, and more.
To launch a specific integration:
ollama launch claude
Supported integrations include Claude Code, Codex, Copilot CLI, DeepSeek Harness, Droid, and OpenCode.
Use OpenClaw to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more:
ollama launch openclaw
Run and chat with Gemma 4:
ollama run gemma4
See ollama.com/library for the full list.
See the quickstart guide for more details.
Ollama has a REST API for running and managing models.
curl http://localhost:11434/api/chat -d '{
"model": "gemma4",
"messages": [{
"role": "user",
"content": "Why is the sky blue?"
}],
"stream": false
}'
See the API documentation for all endpoints.
pip install ollama
from ollama import chat
response = chat(model='gemma4', messages=[
{
'role': 'user',
'content': 'Why is the sky blue?',
},
])
print(response.message.content)
npm i ollama
import ollama from "ollama";
const response = await ollama.chat({
model: "gemma4",
messages: [{ role: "user", content: "Why is the sky blue?" }],
});
console.log(response.message.content);
Want to add your project? Open a pull request.
SwiftChat, Enchanted, Maid, Ollama App, Reins, and ConfiChat listed above also support mobile platforms.
345 followers · starred Sep 2025
2,248 followers · starred May 2025
413 followers · starred Feb 2025
22 followers · starred Feb 2025