Local LLM Setup with Ollama

# Recommended for coding tasks
ollama pull qwen2.5-coder:14b

# Or for general tasks
ollama pull llama3.2:latest

# List installed models
ollama list

ollama serve
# Server runs at http://localhost:11434

npm install -g squads-cli
squads init

# .agents/squads/local/code-reviewer.md

---
provider: ollama
model: qwen2.5-coder:14b
---

# Code Reviewer

## Purpose
Review code changes for bugs, security issues, and improvements.

## Instructions
1. Read the provided code diff
2. Identify potential issues
3. Suggest improvements
4. Format as actionable feedback

squads run local/code-reviewer --execute

# .agents/squads/local/SQUAD.md
---
name: local
mission: Privacy-first local development

providers:
  default: ollama
  model: qwen2.5-coder:7b
---

---
provider: ollama
model: mixtral:8x7b
temperature: 0.3
---

# Deep Analyzer

Uses larger model for complex analysis tasks.

# .env
OLLAMA_HOST=http://localhost:11434
OLLAMA_MODEL=qwen2.5-coder:7b

# .agents/squads/local/SQUAD.md
---
providers:
  default: openai  # LM Studio uses OpenAI-compatible API
  base_url: http://localhost:1234/v1
  model: local-model
---

# Increase context window (uses more VRAM)
ollama run qwen2.5-coder:7b --num-ctx 8192

# Use GPU layers (faster inference)
OLLAMA_NUM_GPU=999 ollama serve

# Q4 quantization (smallest, fastest)
ollama pull qwen2.5-coder:7b-q4_0

# Q8 quantization (balanced)
ollama pull qwen2.5-coder:7b-q8_0

# .agents/squads/engineering/SQUAD.md
---
providers:
  # Local for development
  development:
    provider: ollama
    model: qwen2.5-coder:7b

  # Cloud for production
  production:
    provider: anthropic
    model: claude-sonnet-4
---

# Development (local)
SQUADS_ENV=development squads run engineering

# Production (cloud)
SQUADS_ENV=production squads run engineering

# Check Ollama is running
curl http://localhost:11434/api/tags

# Restart Ollama
ollama serve

# Use smaller model
ollama pull qwen2.5-coder:3b

# Or use CPU-only (slower but works)
OLLAMA_NUM_GPU=0 ollama serve