Cline
Open-source AI coding agent for VS Code. Autonomously explores your codebase, edits files, runs terminal commands, and uses browser automation.
Coding Agent
Yes
Yes
Yes
Yes — for local inference
Autonomous multi-file coding with cloud models
Medium
VS Code, CLI
Open source — free
Cline is Open-source AI coding agent for VS Code. Autonomously explores your codebase, edits files, runs terminal commands, and uses browser automation. Cline (formerly Claude Dev) is the most popular open-source AI coding agent with 58K+ GitHub stars.
Cline 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. Cline is open source (https://github.com/cline/cline), so you can inspect the code and self-host. 24 GB VRAM recommended for local coding models. 12 GB is NOT sufficient for serious agentic coding — Cline's ~15K token system prompt alone consumes significant context. 16 GB is borderline for 14B models at Q4 with short context.
Can it run on my hardware?
Minimum
24 GB VRAM recommended for local coding models. 12 GB is NOT sufficient for serious agentic coding — Cline's ~15K token system prompt alone consumes significant context. 16 GB is borderline for 14B models at Q4 with short context.
Recommended
RTX 3090 or 4090 (24 GB) is the community-verified sweet spot. Can run Qwen3-Coder 30B at Q4 with 40K+ context. For 70B models, dual RTX 3090s (48 GB total) or Apple M4 Max 64GB+ is recommended.
Approximate VRAM needed for recommended local models at Q4 with 8K context:
| Model | Params | Q4 VRAM | Min GPU |
|---|---|---|---|
| Qwen3 30B-A3B (MoE) | 30B | ~19.8 GB | 24 GB |
| Qwen 2.5 Coder 32B Instruct | 32.5B | ~22.9 GB | 24 GB |
| Qwen 2.5 Coder 32B Instruct | 32.5B | ~22.9 GB | 24 GB |
| Qwen3 32B | 32.8B | ~22.2 GB | 24 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 Cline is moderate in complexity. It runs on vscode, cli. Full documentation is available at https://docs.cline.bot.
Limitations
- 12 GB VRAM or less — system prompt alone overwhelms small GPUs
- Non-Anthropic models — tool-calling reliability drops significantly
- Simple autocomplete (use Continue or Copilot instead)
Related
Recommended GPUs
Compatible models
Frequently asked questions
- What is Cline?
- Cline is Open-source AI coding agent for VS Code. Autonomously explores your codebase, edits files, runs terminal commands, and uses browser automation. Cline (formerly Claude Dev) is the most popular open-source AI coding agent with 58K+ GitHub stars.
- Does Cline need a GPU?
- 24 GB VRAM recommended for local coding models. 12 GB is NOT sufficient for serious agentic coding — Cline's ~15K token system prompt alone consumes significant context. 16 GB is borderline for 14B models at Q4 with short context.
- Can Cline use OpenRouter?
- Yes. Cline supports OpenRouter for accessing 300+ models through a single API. See the official setup guide for details.
- Can Cline use local models via Ollama?
- Yes. Cline works with Ollama for running models locally. Install Ollama, pull your model (e.g., `ollama pull qwen2.5:7b`), and connect Cline to the local Ollama server. GPU requirements depend on the model you choose, not Cline itself.
- What is the best local model for Cline?
- For Cline, the community-verified best local model is Qwen3 30B-A3B (MoE). RTX 3090 or 4090 (24 GB) is the community-verified sweet spot. Can run Qwen3-Coder 30B at Q4 with 40K+ context. For 70B models, dual RTX 3090s (48 GB total) or Apple M4 Max 64GB+ is recommended.
- Can I run Cline on 12 GB VRAM?
- 12 GB VRAM is generally not sufficient for serious agentic coding with Cline. 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 Cline free and open source?
- Yes. Cline is open source and completely free. You can find the source code on GitHub at https://github.com/cline/cline.