ollamaollama models

Ollama Setup for Odysseus

Odysseus is the workspace; Ollama is the local AI engine. Install Ollama, pull a model, connect it in Settings — no API key required.

Quick answer

Download Ollama, run ollama pull qwen3.5:0.8b, then add http://localhost:11434/v1 in Odysseus Settings.

Model recommender

Start smaller — a working tiny model beats a huge one that crashes.

System RAM

GPU VRAM

Recommended: qwen3.5:0.8b

Fastest on 8 GB RAM or CPU-only machines.

terminal
ollama pull qwen3.5:0.8b

Best Ollama models for Odysseus

Pick based on your RAM and GPU. When in doubt, start small.

ModelRAMVRAMNotes
qwen3.5:0.8b8 GBNone (CPU)Fastest start — good for testing Odysseus on low-end PCs
llama3.2:3b8–16 GBOptionalBalanced small model for everyday chat
llama3.216 GB8 GB recommendedBetter quality — needs more RAM or a GPU
mistral16 GB8 GB recommendedStrong general-purpose model
qwen2.5:14b32 GB12 GB+High quality — for powerful machines only

Need more detail on hardware? GPU & RAM requirements

Install & pull a model

terminal
# Install Ollama from https://ollama.com/download
# Then pull a model (pick one based on your hardware):

ollama pull qwen3.5:0.8b    # 8 GB RAM, no GPU — fastest start
ollama pull llama3.2:3b     # 8–16 GB RAM
ollama pull llama3.2        # 16 GB RAM, GPU helps

# Verify:
ollama list

Connect Ollama in Odysseus Settings

Native install (no Docker)

terminal
# In Odysseus → Settings → add model endpoint:
http://localhost:11434/v1

Odysseus in Docker

terminal
# Odysseus in Docker + Ollama on host:

# Windows / Mac Docker:
http://host.docker.internal:11434/v1

# Linux Docker:
http://172.17.0.1:11434/v1

# Keep Ollama running (system tray or: ollama serve)

Windows walkthrough with screenshots: /install/windows

FAQ

Common questions