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 b68b112bd8 mlxrunner: release the buffers weight loading leaves in the MLX pool
Loading a model can transform tensors after reading them: qwen3.5 models
pack their linear-attention projections into one layout, and MoE models
fuse the gate and up expert stacks. The buffers those transforms consume
go back to MLX's allocator pool rather than to the system, and nothing
releases the pool until the first request finishes. On qwen3.8:27b-mlx
that is 2.15 GiB held idle on top of 16.9 GiB of weights, counted in the
runner's reported memory the whole time.

Clear the pool once the weights are evaluated. Models whose tensors load
unchanged, such as gemma4, leave nothing in the pool and are unaffected.
2026-09-10 17:25:34 -07:00
.github ci: bound and cache the macOS MLX payload build (#18240) 2026-09-04 14:38:05 -07:00
agent agent: allow multiple edits per edit tool call (#17711) 2026-08-12 16:45:53 -07:00
anthropic Report cached prompt tokens (#17943) 2026-09-02 09:30:44 -07:00
api app: add Ollama to ChatGPT Desktop (#18236) 2026-09-04 14:04:48 -07:00
app app: fix ChatGPT model selector spacing (#18347) 2026-09-09 15:02:42 -07:00
auth
cmake MLX, MLX-C: version bump (#18080) 2026-09-01 16:24:04 -07:00
cmd app: open Codex by default for Ollama launches (#18323) 2026-09-08 13:40:20 -07:00
convert
discover
docs Report cached prompt tokens (#17943) 2026-09-02 09:30:44 -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 server: extract GGUF metadata and unify capabilities (#17858) 2026-09-10 11:16:37 -07:00
harmony
integration fix(docs): correct typos found during code review (#17579) 2026-08-31 08:59:55 -07:00
internal proxy: normalize namespaced commands in Full Access (#18331) 2026-09-09 10:20:48 -07:00
llama llama.cpp: version bump b10729 (#18160) 2026-09-01 16:24:15 -07:00
llm llm: raise token repeat limit to 100 and return error instead of silently closing (#18374) 2026-09-10 15:46:58 -07:00
logutil
manifest server: extract GGUF metadata and unify capabilities (#17858) 2026-09-10 11:16:37 -07:00
middleware openai: finalize responses at the web search limit (#18328) 2026-09-08 16:27:20 -07:00
ml lint fix (#18081) 2026-08-27 17:01:54 -07:00
model fix(docs): correct typos found during code review (#17579) 2026-08-31 08:59:55 -07:00
openai openai: support standalone named function outputs (#18348) 2026-09-09 14:51:50 -07:00
parser
progress fix data races in progress and sched (#18319) 2026-09-08 13:13:59 -07:00
readline
runner
scripts build: go deps (#18161) 2026-09-01 12:59:48 -07:00
server server: extract GGUF metadata and unify capabilities (#17858) 2026-09-10 11:16:37 -07:00
template
thinking
tokenizer tokenizer: fix multi-regex BPE offset handling (#15844) 2026-04-27 14:14:27 -07:00
tools
types Honor model generation defaults (#16471) 2026-09-01 14:52:07 -07:00
version
x mlxrunner: release the buffers weight loading leaves in the MLX pool 2026-09-10 17:25:34 -07:00
.dockerignore
.gitattributes
.gitignore
.golangci.yaml
AGENTS.md Add AGENTS.md and CLAUDE.md to root repository (#16604) 2026-06-07 10:57:59 -07:00
CLAUDE.md
CMakeLists.txt
CMakePresets.json
CONTRIBUTING.md
Dockerfile MLX, MLX-C: version bump (#18080) 2026-09-01 16:24:04 -07:00
go.mod build: go deps (#18161) 2026-09-01 12:59:48 -07:00
go.sum build: go deps (#18161) 2026-09-01 12:59:48 -07:00
LICENSE
LLAMA_CPP_VERSION llama.cpp: version bump b10864 (#18317) 2026-09-10 08:09:59 -07:00
main.go
MLX_C_VERSION MLX, MLX-C: version bump (#18080) 2026-09-01 16:24:04 -07:00
MLX_VERSION MLX, MLX-C: version bump (#18080) 2026-09-01 16:24:04 -07:00
README.md launch: add DeepSeek Harness integration (#17733) 2026-08-13 15:19:02 -07:00
SECURITY.md

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