> ## Documentation Index > Fetch the complete documentation index at: https://docs.namastex.ai/llms.txt > Use this file to discover all available pages before exploring further. # Open Source Agents > Run AI coding agents locally with OpenCode and Qwen ## Overview Run powerful AI coding agents **completely local** - no API keys, no cloud services, no data leaving your machine. Perfect for privacy-sensitive work, learning, or unlimited free usage. **Privacy First**: All code stays on your machine. No external API calls. *** ## Supported Models ### OpenCode **Open-source coding model** * **By**: Open-source community * **Size**: 15B parameters * **Context**: 16K tokens * **Requirements**: 16GB+ RAM, GPU recommended * **License**: Apache 2.0 Best for: General coding, privacy-sensitive work ### Qwen Code **Alibaba's open-source coder** * **By**: Alibaba DAMO Academy * **Size**: 7B, 14B, 32B parameters * **Context**: 32K tokens * **Requirements**: 8GB-64GB RAM depending on size * **License**: Apache 2.0 Best for: Cost-conscious development, competitive with commercial *** ## Quick Start with Ollama [Ollama](https://ollama.ai) makes running local models easy: ```bash theme={null} # macOS brew install ollama # Linux curl https://ollama.ai/install.sh | sh # Windows # Download from https://ollama.ai ``` ```bash theme={null} ollama serve ``` Runs on [http://localhost:11434](http://localhost:11434) ```bash theme={null} # OpenCode ollama pull opencode # Qwen Code (choose size) ollama pull qwen2.5-coder:7b # Small, fast ollama pull qwen2.5-coder:14b # Balanced ollama pull qwen2.5-coder:32b # Best quality ``` Edit `.forge/config.json`: ```json theme={null} { "llms": { "opencode": { "type": "ollama", "model": "opencode", "endpoint": "http://localhost:11434" }, "qwen": { "type": "ollama", "model": "qwen2.5-coder:32b", "endpoint": "http://localhost:11434" } } } ``` ```bash theme={null} forge task create \ --title "Test local model" \ --description "Print 'Hello from OpenCode!'" \ --llm opencode ``` *** ## Hardware Requirements ### Minimum Specs | Model | RAM | GPU | Storage | Speed | | ------------ | ---- | ----------- | ------- | ------ | | **Qwen 7B** | 8GB | Optional | 5GB | Good | | **Qwen 14B** | 16GB | Recommended | 10GB | Better | | **OpenCode** | 16GB | Recommended | 12GB | Good | | **Qwen 32B** | 32GB | Required | 25GB | Best | ### Recommended Setup For best experience: ``` CPU: Modern multi-core (8+ cores) RAM: 32GB+ GPU: NVIDIA RTX 3060+ (12GB VRAM) or Apple Silicon M1/M2/M3 Storage: SSD with 50GB+ free space ``` **Apple Silicon users**: Metal acceleration makes M1/M2/M3 excellent for local models! *** ## Configuration ### Basic Ollama Setup ```json theme={null} { "llms": { "opencode": { "type": "ollama", "model": "opencode", "endpoint": "http://localhost:11434" } } } ``` ### Advanced Configuration ```json theme={null} { "llms": { "qwen": { "type": "ollama", "model": "qwen2.5-coder:32b", "endpoint": "http://localhost:11434", "options": { "temperature": 0.7, "num_ctx": 32768, // Context window "num_predict": 2048, // Max output tokens "top_p": 0.9, "top_k": 40, "repeat_penalty": 1.1 }, "timeout": 120000 // 2 minutes } } } ``` ### GPU Acceleration Enable GPU support for faster inference: ```json theme={null} { "llms": { "qwen": { "type": "ollama", "model": "qwen2.5-coder:32b", "options": { "num_gpu": 1, // Number of GPUs "main_gpu": 0, // Primary GPU index "low_vram": false // Enable for under 8GB VRAM } } } } ``` *** ## Strengths of Local Models ### Complete Privacy * Code never leaves your machine * No API calls to external services * No telemetry or tracking * Perfect for sensitive codebases * GDPR compliant by design * No third-party data sharing * Full audit trail * Meets enterprise security requirements ### No Usage Limits ```bash theme={null} # Unlimited usage! forge task create "Task 1" --llm qwen forge task create "Task 2" --llm qwen forge task create "Task 3" --llm qwen # ... as many as you want # No rate limits # No token costs # No monthly fees ``` ### No Internet Required Work anywhere: * ✈️ On airplanes * 🏔️ Remote locations * 🔌 During outages * 🔒 Air-gapped environments *** ## Limitations ### Lower Quality Local models are less capable than cloud models: | Task Type | Local | Claude | GPT-4 | | ---------------- | ----- | ------ | ----- | | **Simple fixes** | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | | **Architecture** | ⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | | **Bug fixing** | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | | **Testing** | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ### Slower ```bash theme={null} # Speed comparison: "Add authentication" Gemini Flash: 2m 15s ⚡ Claude Sonnet: 5m 22s GPT-4 Turbo: 6m 01s Qwen 32B: 12m 30s (local) OpenCode: 15m 45s (local) ``` ### Hardware Intensive * Requires powerful machine * GPU strongly recommended * High RAM usage * Slower on CPU-only *** ## Best Use Cases ### Privacy-Sensitive Work ```bash theme={null} # Medical records processing forge task create \ --title "Process patient data" \ --files "data/patients/*.csv" \ --llm qwen # Stays local! ``` ### Learning & Experimentation ```bash theme={null} # Unlimited free usage for learning forge task create "Try approach 1" --llm opencode forge task create "Try approach 2" --llm opencode forge task create "Try approach 3" --llm opencode # ... no cost! ``` ### Air-Gapped Environments ```bash theme={null} # Government, military, high-security environments # No internet connection required forge task create "Classified work" --llm qwen ``` ### Cost Reduction ```bash theme={null} # After initial hardware investment # Zero ongoing costs forge task create "Feature 1" --llm qwen # $0 forge task create "Feature 2" --llm qwen # $0 forge task create "Feature 3" --llm qwen # $0 ``` *** ## Model Comparison ### OpenCode vs Qwen | Feature | OpenCode | Qwen 7B | Qwen 14B | Qwen 32B | | ------------ | -------- | ----------- | -------- | -------- | | **Quality** | ⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | | **Speed** | ⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐ | | **RAM** | 16GB | 8GB | 16GB | 32GB | | **Best for** | General | Quick tasks | Balanced | Quality | ### Local vs Cloud | Feature | Local (Qwen 32B) | Claude Sonnet | Gemini Pro | | ----------- | -------------------------- | -------------------------- | ------------------------ | | **Privacy** | ⭐⭐⭐⭐⭐ | ⭐⭐ | ⭐⭐ | | **Quality** | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | | **Speed** | ⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | | **Cost** | \$\$\$ hardware, \$0 usage | \$0 hardware, \$\$\$ usage | \$0 hardware, \$\$ usage | *** ## Performance Optimization ### Use GPU ```bash theme={null} # Check GPU usage nvidia-smi # Or on Mac system_profiler SPDisplaysDataType ``` ### Adjust Context Window ```json theme={null} { "llms": { "qwen": { "options": { "num_ctx": 16384 // Reduce for speed } } } } ``` ### Use Smaller Models for Simple Tasks ```bash theme={null} # Simple task → Qwen 7B (fast) forge task create "Add comment" --llm qwen-7b # Complex task → Qwen 32B (quality) forge task create "Refactor architecture" --llm qwen-32b ``` *** ## Troubleshooting **Error**: "Connection refused to localhost:11434" **Solution**: ```bash theme={null} # Start Ollama ollama serve # Or as background service (Linux) systemctl start ollama # macOS (via brew services) brew services start ollama ``` **Error**: "Failed to allocate memory" **Solutions**: * Use smaller model (7B instead of 32B) * Close other applications * Enable low VRAM mode: ```json theme={null} { "llms": { "qwen": { "options": { "low_vram": true } } } } ``` * Upgrade RAM **Issue**: Model taking forever **Solutions**: * Enable GPU acceleration * Use smaller model * Reduce context window * Close background apps * Check CPU usage (should be high) **Error**: "Model 'qwen2.5-coder:32b' not found" **Solution**: ```bash theme={null} # Pull the model ollama pull qwen2.5-coder:32b # List available models ollama list # Check model size before pulling ollama show qwen2.5-coder:32b ``` *** ## Cost Analysis ### Hardware Investment ``` One-time costs: ├── Mid-range GPU (RTX 4060): $300 ├── Additional RAM (32GB): $100 └── SSD storage (1TB): $80 ──────────────────────────── Total: ~$480 Break-even vs Claude: $480 / $50/month = ~10 months of usage ``` ### Ongoing Costs ``` Electricity: ├── GPU power: ~200W ├── Running 8hrs/day └── Cost: ~$5-10/month vs Cloud APIs: ├── Claude: $50-200/month typical usage ├── GPT-4: $80-300/month └── Gemini: $0-50/month (free tier) ``` **Heavy users** (>\$100/month on APIs) break even quickly with local setup! *** ## Best Practices ```bash theme={null} # Proprietary code forge task create \ --title "Refactor proprietary algorithm" \ --llm qwen # Stays local ``` Begin with Qwen 7B: ```bash theme={null} ollama pull qwen2.5-coder:7b ``` Upgrade to 32B if needed ```bash theme={null} # Check resource usage htop nvidia-smi # GPU # Adjust if needed ``` ```bash theme={null} # Quick iteration: local forge task create "Try A" --llm qwen # Final polish: cloud forge task fork 1 --llm claude ``` Best of both worlds! *** ## Hybrid Strategy Combine local and cloud models: ### Strategy 1: Privacy Tiers ```bash theme={null} # Sensitive code → local forge task create \ --title "Process customer data" \ --llm qwen # Public code → cloud (faster, better) forge task create \ --title "Update README" \ --llm gemini ``` ### Strategy 2: Cost Optimization ```bash theme={null} # Experimentation → local (free) forge task create "Try approach A" --llm qwen forge task create "Try approach B" --llm qwen forge task create "Try approach C" --llm qwen # Production → cloud (quality) forge task fork --llm claude ``` ### Strategy 3: Network-Aware ```bash theme={null} # Offline → local if ping -c 1 8.8.8.8 >/dev/null 2>&1; then LLM=gemini # Online, use fast cloud else LLM=qwen # Offline, use local fi forge task create "Task" --llm $LLM ``` *** ## Real-World Example ### Setup for Privacy-First Development ```bash theme={null} # 1. Install Ollama brew install ollama # 2. Pull Qwen 32B (best quality) ollama pull qwen2.5-coder:32b # 3. Configure Forge cat > .forge/config.json < Get started with local models Compare with cloud agents Privacy-first development patterns Browse available models