# macOS/Linux
-weight: 500;">curl -fsSL https://ollama.com/-weight: 500;">install.sh | sh # Windows - download from ollama.com
# macOS/Linux
-weight: 500;">curl -fsSL https://ollama.com/-weight: 500;">install.sh | sh # Windows - download from ollama.com
# macOS/Linux
-weight: 500;">curl -fsSL https://ollama.com/-weight: 500;">install.sh | sh # Windows - download from ollama.com
# Best overall for coding (needs 16GB+ RAM)
ollama pull deepseek-coder-v2:16b # Lighter option (8GB RAM)
ollama pull codellama:7b # For code review and explanations
ollama pull mistral:7b
# Best overall for coding (needs 16GB+ RAM)
ollama pull deepseek-coder-v2:16b # Lighter option (8GB RAM)
ollama pull codellama:7b # For code review and explanations
ollama pull mistral:7b
# Best overall for coding (needs 16GB+ RAM)
ollama pull deepseek-coder-v2:16b # Lighter option (8GB RAM)
ollama pull codellama:7b # For code review and explanations
ollama pull mistral:7b
ollama run deepseek-coder-v2:16b
>>> Write a Python function to parse JSON from a file safely
ollama run deepseek-coder-v2:16b
>>> Write a Python function to parse JSON from a file safely
ollama run deepseek-coder-v2:16b
>>> Write a Python function to parse JSON from a file safely
{ "models": [ { "title": "DeepSeek Coder Local", "provider": "ollama", "model": "deepseek-coder-v2:16b" } ], "tabAutocompleteModel": { "title": "CodeLlama", "provider": "ollama", "model": "codellama:7b" }
}
{ "models": [ { "title": "DeepSeek Coder Local", "provider": "ollama", "model": "deepseek-coder-v2:16b" } ], "tabAutocompleteModel": { "title": "CodeLlama", "provider": "ollama", "model": "codellama:7b" }
}
{ "models": [ { "title": "DeepSeek Coder Local", "provider": "ollama", "model": "deepseek-coder-v2:16b" } ], "tabAutocompleteModel": { "title": "CodeLlama", "provider": "ollama", "model": "codellama:7b" }
}
# Check if Ollama detects your GPU
ollama ps # Should show CUDA if working
# Check if Ollama detects your GPU
ollama ps # Should show CUDA if working
# Check if Ollama detects your GPU
ollama ps # Should show CUDA if working
# Terminal 1 - for chat
ollama serve # Terminal 2 - load models
ollama run deepseek-coder-v2:16b # stays in memory
# Terminal 1 - for chat
ollama serve # Terminal 2 - load models
ollama run deepseek-coder-v2:16b # stays in memory
# Terminal 1 - for chat
ollama serve # Terminal 2 - load models
ollama run deepseek-coder-v2:16b # stays in memory
ollama -weight: 500;">stop deepseek-coder-v2:16b
ollama -weight: 500;">stop deepseek-coder-v2:16b
ollama -weight: 500;">stop deepseek-coder-v2:16b - Privacy - Your code never leaves your machine
- Cost - Zero ongoing fees after initial setup
- Speed - No network latency, works offline - Open VS Code
- Extensions → Search "Continue"
- Open Continue sidebar (Cmd/Ctrl + L) - Chat with your codebase (Cmd+L)
- Inline edits (Cmd+I)
- Tab autocomplete - Autocomplete (feels like Copilot)
- Explaining code
- Writing boilerplate
- Simple refactoring
- Regex and SQL generation - Complex multi-file changes
- Understanding large codebases
- Subtle bug detection - Cutting-edge reasoning (still reach for Claude for architecture)
- Very large context windows
