Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. https://ollama.com
Find a file
Jesse Gross c01eafa552 mlxrunner: settle the draft caches when a prefill is cancelled
A prefill settles the drafter with the seed token after its last chunk,
leveling the draft caches with the targets; a cancelled prefill
returned before that, leaving the targets one token past the draft
caches and the recorded keys. The next request then had to move every
cache, and models with recurrent layers, which cannot rewind, fell back
to the last snapshot: a retry after a client timeout lost up to a full
snapshot interval of the prompt it had just evaluated.

Settle with the next prompt token on the cancelled path too. The caches
then rest level with the recorded keys, and a retry resumes exactly
where the prefill stopped.
2026-08-21 09:58:33 -07:00
.github Release v0.32.7 (#17646) 2026-08-10 04:04:56 -07:00
agent agent: allow multiple edits per edit tool call (#17711) 2026-08-12 16:45:53 -07:00
anthropic app: add claude desktop app (#17899) 2026-08-20 14:03:43 -07:00
api openai: support web search in Responses API (#17686) 2026-08-12 11:51:54 -07:00
app polish onboarding layout and disable zoom (#17885) 2026-08-20 17:03:58 -04:00
auth auth: fix problems with the ollama keypairs (#12373) 2025-09-22 23:20:20 -07:00
cmake mlx: fix mac assumptions on linux/windows (#17898) 2026-08-20 09:50:10 -07:00
cmd launch: fall back to npx for DeepSeek Harness (#17758) 2026-08-20 14:04:44 -07:00
convert lint fixes (#17897) 2026-08-20 10:23:25 -07:00
discover lint fixes (#17897) 2026-08-20 10:23:25 -07:00
docs docs: register DeepSeek Harness (#17751) 2026-08-14 14:30:21 -07:00
envconfig runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
format
fs create: harden GGUF create flows (#17062) 2026-07-06 16:20:20 -07:00
harmony runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
integration renderers/qwen: tolerate non-leading system messages (#17757) 2026-08-14 14:12:50 -07:00
internal app: add claude desktop app (#17899) 2026-08-20 14:03:43 -07:00
llama llama.cpp update (#17545) 2026-08-04 09:51:52 -07:00
llm llm: transcode WebP images for llama-server (#17755) 2026-08-14 13:21:11 -07:00
logutil runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
manifest runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
middleware openai: support web search in Responses API (#17686) 2026-08-12 11:51:54 -07:00
ml llama: enable FA on CUDA CC 6.x GPUs (#16994) 2026-07-02 17:11:39 -07:00
mlx/compat mlx update (#17850) 2026-08-19 07:15:11 -07:00
model qwen3.8: normalize system messages (#17855) 2026-08-19 13:08:09 -07:00
openai launch: add Muse Code integration (#17594) 2026-08-13 13:10:29 -07:00
parser model: add Laguna v8 chat support and fix Metal inference (#17291) 2026-07-21 16:06:29 -07:00
progress progress: fix data races on ticker, states, spinner, and bar state (#17445) 2026-08-04 15:06:15 -07:00
readline lint fixes (#17897) 2026-08-20 10:23:25 -07:00
runner imagegen: remove MLX image generation code (#16615) 2026-07-28 15:35:28 -07:00
scripts win: support CUDA on Windows ARM64 (#16931) 2026-07-21 10:53:30 -07:00
server lint fixes (#17897) 2026-08-20 10:23:25 -07:00
template lint fixes (#17897) 2026-08-20 10:23:25 -07:00
thinking
tokenizer tokenizer: fix multi-regex BPE offset handling (#15844) 2026-04-27 14:14:27 -07:00
tools tools: ignore braces inside JSON strings when detecting tool call end (#16937) 2026-06-27 12:00:55 -07:00
types manifests: remove OCI rootfs from the model config (#17619) 2026-08-08 19:44:57 -07:00
version
x mlxrunner: settle the draft caches when a prefill is cancelled 2026-08-21 09:58:33 -07:00
.dockerignore
.gitattributes .gitattributes: add app/webview to linguist-vendored (#13274) 2025-11-29 23:46:10 -05:00
.gitignore create: Clean up experimental paths, fix create from existing safetensor model (#14679) 2026-04-07 08:12:57 -07:00
.golangci.yaml ci: restore previous linter rules (#13322) 2025-12-03 18:55:02 -08:00
AGENTS.md Add AGENTS.md and CLAUDE.md to root repository (#16604) 2026-06-07 10:57:59 -07:00
CLAUDE.md Add AGENTS.md and CLAUDE.md to root repository (#16604) 2026-06-07 10:57:59 -07:00
CMakeLists.txt mlx: fix mac assumptions on linux/windows (#17898) 2026-08-20 09:50:10 -07:00
CMakePresets.json runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
CONTRIBUTING.md docs: fix typos in repository documentation (#10683) 2025-11-15 20:22:29 -08:00
Dockerfile ci: plumb temporary MLX patch through to docker stages (#17874) 2026-08-19 08:33:53 -07:00
go.mod agent/tui: stream thinking traces (#17611) 2026-08-07 13:11:45 -07:00
go.sum server: remove OLLAMA_EXPERIMENT=client2 (#16962) 2026-07-06 13:15:39 -07:00
LICENSE
LLAMA_CPP_VERSION llama.cpp update (#17851) 2026-08-18 11:53:00 -07:00
main.go
MLX_C_VERSION Update MLX and MLX-C with threading fixes (#15845) 2026-05-03 10:03:14 -07:00
MLX_VERSION mlx update (#17886) 2026-08-20 10:02:41 -07:00
README.md launch: add DeepSeek Harness integration (#17733) 2026-08-13 15:19:02 -07:00
SECURITY.md docs: fix typos in repository documentation (#10683) 2025-11-15 20:22:29 -08:00

ollama

Ollama

Start building with open models.

Download

macOS

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

or download manually

Windows

irm https://ollama.com/install.ps1 | iex

or download manually

Linux

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

Manual install instructions

Docker

The official Ollama Docker image ollama/ollama is available on Docker Hub.

Libraries

Community

Get started

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.

Coding

To launch a specific integration:

ollama launch claude

Supported integrations include Claude Code, Codex, Copilot CLI, DeepSeek Harness, Droid, and OpenCode.

AI assistant

Use OpenClaw to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more:

ollama launch openclaw

Chat with a model

Run and chat with Gemma 4:

ollama run gemma4

See ollama.com/library for the full list.

See the quickstart guide for more details.

REST API

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.

Python

pip install ollama
from ollama import chat

response = chat(model='gemma4', messages=[
  {
    'role': 'user',
    'content': 'Why is the sky blue?',
  },
])
print(response.message.content)

JavaScript

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);

Supported backends

  • llama.cpp project founded by Georgi Gerganov.

Documentation

Community Integrations

Want to add your project? Open a pull request.

Chat Interfaces

Web

Desktop

  • Dify.AI - LLM app development platform
  • AnythingLLM - All-in-one AI app for Mac, Windows, and Linux
  • Maid - Cross-platform mobile and desktop client
  • Witsy - AI desktop app for Mac, Windows, and Linux
  • Cherry Studio - Multi-provider desktop client
  • Ollama App - Multi-platform client for desktop and mobile
  • PyGPT - AI desktop assistant for Linux, Windows, and Mac
  • Alpaca - GTK4 client for Linux and macOS
  • SwiftChat - Cross-platform including iOS, Android, and Apple Vision Pro
  • Enchanted - Native macOS and iOS client
  • RWKV-Runner - Multi-model desktop runner
  • Ollama Grid Search - Evaluate and compare models
  • macai - macOS client for Ollama and ChatGPT
  • AI Studio - Multi-provider desktop IDE
  • Reins - Parameter tuning and reasoning model support
  • ConfiChat - Privacy-focused with optional encryption
  • LLocal.in - Electron desktop client
  • MindMac - AI chat client for Mac
  • Msty - Multi-model desktop client
  • BoltAI for Mac - AI chat client for Mac
  • IntelliBar - AI-powered assistant for macOS
  • Kerlig AI - AI writing assistant for macOS
  • Hillnote - Markdown-first AI workspace
  • Perfect Memory AI - Productivity AI personalized by screen and meeting history

Mobile

SwiftChat, Enchanted, Maid, Ollama App, Reins, and ConfiChat listed above also support mobile platforms.

Code Editors & Development

Libraries & SDKs

Frameworks & Agents

RAG & Knowledge Bases

  • RAGFlow - RAG engine based on deep document understanding
  • R2R - Open-source RAG engine
  • MaxKB - Ready-to-use RAG chatbot
  • Minima - On-premises or fully local RAG
  • Chipper - AI interface with Haystack RAG
  • ARGO - RAG and deep research on Mac/Windows/Linux
  • Archyve - RAG-enabling document library
  • Casibase - AI knowledge base with RAG and SSO
  • BrainSoup - Native client with RAG and multi-agent automation

Bots & Messaging

Terminal & CLI

Productivity & Apps

Observability & Monitoring

  • Opik - Debug, evaluate, and monitor LLM applications
  • OpenLIT - OpenTelemetry-native monitoring for Ollama and GPUs
  • Lunary - LLM observability with analytics and PII masking
  • Langfuse - Open source LLM observability
  • HoneyHive - AI observability and evaluation for agents
  • MLflow Tracing - Open source LLM observability

Database & Embeddings

Infrastructure & Deployment

Cloud

Package Managers