Stack

Ollama + Open WebUILast reviewed: June 2026

Ollama + Open WebUI Starter Stack

A practical local AI stack for beginners: Ollama runs the models, and Open WebUI gives you a private browser-based chat workspace on top.

Best forFirst local AI setup — beginner friendly
Hardware8 GB RAM min · 8 GB VRAM recommended
ToolsOllama · Open WebUI
Time to first result5–10 minutes

Bill of materials

Model runner

Ollama

Runs local models via a REST API on localhost:11434 — the standard local inference backend for this stack

Chat interface (optional)

Open WebUI

Self-hosted browser chat UI; connects to Ollama at localhost:11434 with no cloud dependency — runs via Docker

Starter models

Qwen3 8B

Lightweight 8B model — strong general chat, fits on 8 GB VRAM at Q4_K_M quantization

Phi-4 Mini

Very small footprint — good choice for laptops and low-VRAM tests where speed matters more than depth

Gemma 4

Google open-weight model — efficient, well-documented, reliable default for beginners

Install Ollama and run your first model

1. Install Ollama

One-line install for macOS and Linux. On Windows, download the installer from ollama.com/download.

# macOS / Linux
curl -fsSL https://ollama.ai/install.sh | sh

# Windows (winget)
winget install Ollama.Ollama

2. Pull a small model first

Start with an 8B model. Larger models are available once you know the stack is working.

ollama pull qwen3:8b

3. Run the model in your terminal

ollama run qwen3:8b

4. Add Open WebUI (browser interface via Docker)

Run this after Ollama is working. Opens at http://localhost:3000 — first-run sign-up creates a local-only account with no external connections.

docker run -d \
  -p 3000:8080 \
  --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

Ran the commands? Measure what your setup actually does → — speed, load time, and whether anything is silently throttling it.

Stack components

  • Ollama: local model runtime and API.
  • Open WebUI: self-hosted chat interface for local and hosted model backends.
  • Models: start with smaller Qwen, Gemma, Phi, Mistral, or DeepSeek distilled models.
  • Optional RAG layer: add Qdrant, Chroma, or another vector database later.

Hardware requirements

Start smaller than you think. A reliable 7B or 8B quantized model is a better first milestone than a large model that barely fits and makes every test slow.

TierHardwareModel guidance
Minimum16 GB RAM, CPU-only possibleUse 3B-8B quantized models
Recommended32 GB RAM, NVIDIA GPU with 12 GB+ VRAMUse 7B-14B models comfortably
Best64 GB RAM, 24 GB+ VRAM or server hardwareTry larger 32B-70B quantized models

Recommended first models

Setup path

  1. Install Ollama on your local machine.
  2. Pull one small model first instead of starting with a huge checkpoint.
  3. Run a few prompts directly through Ollama.
  4. Install or run Open WebUI and connect it to Ollama.
  5. Create a test workspace and compare two or three models on the same prompts.
  6. Add RAG, vector search, or MCP tools only after the basic chat stack is stable.

Best for

  • Beginners building their first private local AI setup
  • Developers testing local models before wiring them into apps
  • Teams that want a private browser chat interface over local models
  • Builders who want a foundation for RAG, coding assistants, and MCP workflows

Related pages