Aider
AI pair programming in your terminal. The most local-model-friendly coding agent with a tiny ~2K token system prompt and deep git integration.
Coding Agent
Yes
Yes
Yes
Yes — for local inference
Pair programming with local models on modest hardware
Medium
CLI, macOS, Linux
Open source — free
Aider is AI pair programming in your terminal. The most local-model-friendly coding agent with a tiny ~2K token system prompt and deep git integration. Aider is a CLI-based AI pair programmer with 41K+ GitHub stars.
Aider works with both local models and cloud APIs. It supports OpenRouter for unified access to 300+ models from a single API. Ollama integration lets you run models locally on your own GPU. Aider is open source (https://github.com/Aider-AI/aider), so you can inspect the code and self-host. Aider is the most efficient coding agent for local models. Its ~2K system prompt means you can run 7B models on 8 GB VRAM and 14B models on 12-16 GB VRAM. Configure Ollama context window higher than the default 2K tokens.
Can it run on my hardware?
Minimum
Aider is the most efficient coding agent for local models. Its ~2K system prompt means you can run 7B models on 8 GB VRAM and 14B models on 12-16 GB VRAM. Configure Ollama context window higher than the default 2K tokens.
Recommended
16 GB VRAM for Qwen 2.5 Coder 14B at Q8 with 32K context. 24 GB VRAM for Qwen 2.5 Coder 32B at Q4 with 64K context. CPU-only works for 7B models but expect 5-10x slower.
Approximate VRAM needed for recommended local models at Q4 with 8K context:
| Model | Params | Q4 VRAM | Min GPU |
|---|---|---|---|
| Qwen 2.5 Coder 32B Instruct | 32.5B | ~22.9 GB | 24 GB |
| Qwen3 32B | 32.8B | ~22.2 GB | 24 GB |
| Qwen3 30B-A3B (MoE) | 30B | ~19.8 GB | 24 GB |
| DeepSeek R1 Distill Qwen 32B | 32.5B | ~22.9 GB | 24 GB |
| Qwen3 14B | 14.8B | ~10.8 GB | 12 GB |
App compatibility
| Feature | Supported |
|---|---|
| Local models | Yes |
| OpenRouter | Yes |
| OpenAI-compatible API | Yes |
| Ollama | Yes |
| LM Studio | Yes |
| Anthropic API | Yes |
| Google API | Yes |
| Mistral API | No |
| Docker | No |
| Works offline | No |
| Needs GPU | Yes |
Recommended models
Best local models
Local vs cloud: which should you use?
Use local models if
- You want privacy — data never leaves your machine
- You already have a GPU with sufficient VRAM
- You want zero per-token API costs
- You need offline access
- You have at least 16-24 GB VRAM for recommended models
Use cloud/API if
- Your GPU has insufficient VRAM for the models you need
- You want access to frontier model quality
- You need maximum coding/reasoning performance
- You don't want to manage local model downloads and updates
- OpenRouter lets you switch between 300+ models with one API key
Setup overview
Setting up Aider is moderate in complexity. It runs on cli, macos, linux. Full documentation is available at https://aider.chat/docs.
Limitations
- Autonomous multi-step agentic coding (use Cline instead)
- GUI-only users (CLI-only tool)
- Windows without WSL
Related
Recommended GPUs
Compatible models
Frequently asked questions
- What is Aider?
- Aider is AI pair programming in your terminal. The most local-model-friendly coding agent with a tiny ~2K token system prompt and deep git integration. Aider is a CLI-based AI pair programmer with 41K+ GitHub stars.
- Does Aider need a GPU?
- Aider is the most efficient coding agent for local models. Its ~2K system prompt means you can run 7B models on 8 GB VRAM and 14B models on 12-16 GB VRAM. Configure Ollama context window higher than the default 2K tokens.
- Can I run Aider on CPU only?
- Yes — Aider supports CPU-only operation, but performance will be significantly slower (5-10x) compared to GPU inference. CPU-only works best for models under 7B parameters with at least 16 GB of system RAM.
- Can Aider use OpenRouter?
- Yes. Aider supports OpenRouter for accessing 300+ models through a single API. Configure OpenRouter as a provider in Aider's settings with your API key.
- Can Aider use local models via Ollama?
- Yes. Aider works with Ollama for running models locally. Install Ollama, pull your model (e.g., `ollama pull qwen2.5:7b`), and connect Aider to the local Ollama server. GPU requirements depend on the model you choose, not Aider itself.
- What is the best local model for Aider?
- For Aider, the community-verified best local model is Qwen 2.5 Coder 32B Instruct. 16 GB VRAM for Qwen 2.5 Coder 14B at Q8 with 32K context. 24 GB VRAM for Qwen 2.5 Coder 32B at Q4 with 64K context. CPU-only works for 7B models but expect 5-10x slower.
- Can I run Aider on 12 GB VRAM?
- 12 GB VRAM is generally not sufficient for serious agentic coding with Aider. You can run smaller models (7B-14B at Q4) but tool-calling reliability and context handling will be limited. For the best experience, 24 GB VRAM (RTX 3090/4090) is the community-recommended minimum for local agentic coding.
- Is Aider free and open source?
- Yes. Aider is open source and completely free. You can find the source code on GitHub at https://github.com/Aider-AI/aider.