Ollama

Local-first

Run AI models locally with complete privacy

AI Coding Assistants ollama.com GitHub · 175k ★ CLI macOS Windows Linux API

Coding Text / Chat Agents

Try Ollama

About

Ollama lets you run large language models on your own hardware for complete data privacy. Access 40,000+ community integrations and run open models locally or use cloud GPUs. GPU-time billing ensures no token caps.

Key Features

Run models locally40,000+ integrationsGPU-time cloud billingNo token caps locallyAll major open models

Pros

Complete data privacy on local hardware
40,000+ community integrations
No token limits, GPU-time billing
Works with all major open-source models
Free tier with unlimited local usage

Cons

Cloud features require paid plan
Team plan not yet available

Pricing Plans

Free

Local models, CLI & API

Free

Download

Unlimited local model usage
Run 1 cloud model at a time
CLI & API access

Pro

Cloud GPUs, 3 concurrent models

$20/mo

Get Pro

$60 of cloud usage credits per month
Run 3 cloud models at a time
Upload & share private models

Max

10 concurrent cloud models

$100/mo

Get Max

$300 of cloud usage credits per month
Run 10 cloud models at a time
Built for continuous agent workloads

Team

Unlimited users, shared credits

$500/mo

Get Team

$1,000 usage credits included
Unlimited users
Centralized billing

Enterprise

Custom pricing for organizations

Custom

Get Started

Free

Local models, CLI & API

Free

Download

Unlimited local model usage
Run 1 cloud model at a time
CLI & API access

Pro

Cloud GPUs, 3 concurrent models

$20/mo

Get Pro

$60 of cloud usage credits per month
Run 3 cloud models at a time
Upload & share private models

Max

10 concurrent cloud models

$100/mo

Get Max

$300 of cloud usage credits per month
Run 10 cloud models at a time
Built for continuous agent workloads

Team

Unlimited users, shared credits

$500/mo

Get Team

$1,000 usage credits included
Unlimited users
Centralized billing

Enterprise

Custom pricing for organizations

Custom

Get Started

1–3 of 5

Supported AI Models

GOSS

gpt-oss:120b

OpenAI (open-weight) / API

Coding Text / Chat Agents

Context Window

—

Latency (TTFT)

—

Pricing (Input)

Included

Pricing (Output)

Included

Q3C

Qwen3-Coder:480b

Alibaba / API

Coding Text / Chat Agents

Context Window

—

Latency (TTFT)

—

Pricing (Input)

Included

Pricing (Output)

Included

G51

GLM-5.1

Zhipu AI / API

Coding Text / Chat Agents

Context Window

—

Latency (TTFT)

—

Pricing (Input)

Included

Pricing (Output)

Included

K26

Kimi-K2.6

Moonshot AI / API

Coding Text / Chat Agents

Context Window

—

Latency (TTFT)

—

Pricing (Input)

Included

Pricing (Output)

Included

Highlights

🔒

Full Privacy

📖

Open Models

∞

No Token Caps

At a Glance

InterfaceCLI / Terminal · macOS · Windows · Linux · API

Model Supportgpt-oss:120b, Qwen3-Coder:480b +2 more

PriceFree / $20–$500/mo

Agent Mode

Terminal Access

IDE Integration

Multi-file Editing

Best ForRun AI models locally with complete privacy

Features

Models

gpt-oss:120b

Qwen3-Coder:480b

GLM-5.1

Kimi-K2.6

Capabilities

Code Generation

Agent Workflows

Key Features

Run models locally

40,000+ integrations

GPU-time cloud billing

No token caps locally

All major open models

Real-World Task Ratings

Build Next.js SaaS

5/10

Fix Production Bug

5/10

Refactor Legacy Code

5/10

Create API

5/10

Write Tests

5/10

Cost Breakdown

Local UsageFree

Pro Cloud$20/mo

Max Cloud$100/mo

Est. Monthly Spend$0–100

Context & Memory

Context Window

Model-dependent

Repo Understanding

★★★★★

Memory

★★★★★

Autonomy Score

Edit 1 File

5/10

Edit 10 Files

4/10

Create Feature

4/10

Deploy App

3/10

Fix Unknown Bug

4/10

Overall Average4.0/10

Community

175k+

GitHub Stars

40,000+

Community Integrations

Weekly

Release Frequency

Killer Features

Can Build Entire App

4/10

Vibe Coding Score

5/10

Full Breakdown

Basics

InterfaceCLI / Terminal · macOS · Windows · Linux · API

CategoryAI Coding Assistants

Open source

Multi-language support

Websiteollama.com

AI Capabilities

Modelsgpt-oss:120b, Qwen3-Coder:480b +2 more

Context windowModel-dependent

Agentic execution

Code generation

Multimodal input

Workflow

CLI / Terminal

IDE plugin

Web interface

API access

Desktop app

Pricing

FreeFree

Pro$20/mo

Max$100/mo

Team$500/mo

EnterpriseCustom

Ideal For

Privacy-First DevsOffline WorkOpen-Source ModelsSelf-Hosted AI

Choose This Plan If…

Complete data privacy on local hardware
40,000+ community integrations
No token limits, GPU-time billing
Works with all major open-source models
Free tier with unlimited local usage