Skip to main content

​
Overview

Ollama allows you to run large language models locally on your Mac. Perfect for privacy-focused work and offline usage.

​
Supported Models

Any model available in Ollama:
ModelSizeBest For
Llama 3.1 70B40GBComplex tasks
Llama 3.1 8B4.7GBGeneral purpose
Mistral 7B4.1GBFast responses
CodeLlama4.7GBProgramming
Phi-32.2GBLightweight
Gemma 25.4GBBalanced
Qwen 2VariousMultilingual

​
Setup

1

Install Ollama

Download from ollama.ai or:
brew install ollama
2

Pull a Model

ollama pull llama3.1
3

Verify Installation

ollama list
4

Configure in EnConvo

  1. Open Settings → AI Provider
  2. Select Ollama
  3. Go to Credentials module
  4. Set endpoint: http://localhost:11434
5

Select Model

Choose from your installed models

​
Configuration

SettingDescriptionDefault
CredentialsEndpoint configurationlocalhost:11434
Model NameInstalled modelllama2:latest
TemperatureCreativity (0-2)Medium (1)

​
Reasoning Mode

Enable thinking for compatible models:
OptionDescription
DisabledStandard responses
ThinkingEnable reasoning
ollama pull llama3.1        # General purpose
ollama pull codellama       # Coding
ollama pull mistral         # Fast
ollama pull phi3            # Lightweight
ollama pull gemma2          # Google's model
ollama pull qwen2           # Multilingual

​
System Requirements

RAMRecommended Models
8GB7B models (Llama 3.1 8B, Mistral 7B)
16GBLarger 7B models, some 13B
32GB13B-30B models
64GB+70B models
Apple Silicon Macs with Metal acceleration provide excellent local LLM performance.

​
Privacy Benefits

Complete Privacy

Data never leaves your Mac

Offline Access

Works without internet

No Usage Limits

Unlimited local queries

Full Control

Choose exactly which models to run

​
Troubleshooting

  • Ensure Ollama is running: ollama serve
  • Check port 11434 is available
  • Verify endpoint in settings
  • Use smaller models
  • Close memory-intensive apps
  • Consider quantized models
  • Use smaller model
  • Reduce context length
  • Restart Ollama