name: minion-models description: > Manage Ollama models for minions. Pull new models, list available ones, switch presets, check disk usage. Use when setting up or changing models. allowed-tools: Bash, Read, Write

Minion Models

Manage Ollama models for your minion squad.

Quick commands

List installed models

ollama list

Pull a model

ollama pull qwen2.5-coder:1.5b

Check model info

ollama show qwen2.5-coder:1.5b

Remove a model

ollama rm qwen2.5-coder:0.5b

Presets

Pull preset models

nano:

ollama pull qwen2.5-coder:0.5b

small (recommended):

ollama pull qwen2.5-coder:1.5b

medium:

ollama pull qwen2.5-coder:7b

large:

ollama pull qwen2.5-coder:14b

Switch preset

Edit llm_gc/config/models.yaml and change the preset line:

preset: small  # Change to: nano, small, medium, or large

Or use sed:

sed -i.bak 's/^preset:.*/preset: medium/' llm_gc/config/models.yaml

Check disk usage

# Total Ollama storage
du -sh ~/.ollama/models

# Per-model breakdown
ls -lh ~/.ollama/models/blobs/ | head -20

Recommended models

Alternative models

# DeepSeek (alternative to Qwen)
ollama pull deepseek-coder:1.3b
ollama pull deepseek-coder:6.7b

# CodeLlama (Meta)
ollama pull codellama:7b

# StarCoder
ollama pull starcoder2:3b

Troubleshooting

Model not found:

ollama pull <model-name>

Slow responses:

• Try smaller model
• Check htop for RAM pressure
• Reduce --workers in swarm

Out of disk space:

# Remove unused models
ollama rm <model-name>

# Check what's installed
ollama list

Model quality issues:

• Upgrade preset: nano → small → medium
• Add more context with --read
• Simplify the task