---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ollama"
name: "Ollama"
category: "Runtimes / Inference"
stack_layer: "runtime"
homepage: "https://ollama.com/"
repo: "https://github.com/ollama/ollama"
docs: "https://docs.ollama.com/"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 183257
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Ollama

> The one-command local model runner with a REST API on port 11434.

**What:** One command to download and run a model. **Why:** The fastest way from zero to a local model.

**Stack layer:** runtime (model → runtime → harness → memory → tools)

A local model runner and server. Pull models by name, chat in the terminal, and call a local REST API. Official Python (ollama-python) and JS (ollama-js) libraries.

**Gap role:** The easiest on-ramp: model management plus a stable local API that harnesses, UIs and memory layers already support.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- macOS, Linux or Windows

## Install

### macOS (Apple Silicon)

1. official script (README lists it for macOS):

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

2. Run:

```bash
# alternatives: brew install ollama   |   brew install --cask ollama-app   |   download https://ollama.com/download/Ollama.dmg
```

### Linux

1. Run:

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

### Windows

1. PowerShell:

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

## Configure

1. example model name used in the README; pick any model from ollama.com/library:

```bash
ollama pull gemma4
```

2. interactive chat:

```bash
ollama run gemma4
```

## Verify

1. Expect: prints a version string

```bash
ollama --version
```

2. Expect: JSON list of locally pulled models

```bash
curl -s http://localhost:11434/api/tags
```

3. Expect: JSON with message.content

```bash
curl -s http://localhost:11434/api/chat -d '{"model":"gemma4","messages":[{"role":"user","content":"hi"}],"stream":false}'
```

## Rollback

1. remove a model:

```bash
ollama rm gemma4
```

2. if installed via Homebrew:

```bash
brew uninstall ollama   # or: brew uninstall --cask ollama-app
```

3. deletes all downloaded models and keys; irreversible:

```bash
rm -rf ~/.ollama
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/ollama.md

## Caveats

- Model names change frequently; confirm on ollama.com/library.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- open-webui (https://insidethemachine.ai/setups/open-webui.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- aider (https://insidethemachine.ai/setups/aider.md)
- mem0 (https://insidethemachine.ai/setups/mem0.md)

## Sources

- https://github.com/ollama/ollama
- https://formulae.brew.sh/formula/ollama
- https://formulae.brew.sh/cask/ollama-app