A local, open-source, and free alternative to expensive coding tool Claude Code is available in the form of Goose and Qwen3-coder. In this article, we’ll explore how these tools work together to create a fully free competitor to Claude Code.
To get started with Goose, Ollama, and Qwen3-coder, download and install both Goose and Ollama first, then configure your connection to Ollama by selecting the qwen3-coder:30b model. Make sure you have enough storage space as the model is 17GB and requires local processing.
Next, set up Goose by choosing a model and configuring your connection to Ollama. Then, test Goose by running simple programming tests and see how it performs with repeated corrections improving the actual codebase.
While Goose’s performance was good overall, it took five tries for the tool to get a test right on the first try, which is slower than other chatbot coding tools like Grok and Gemini. However, this is still an early impression, and further testing will be needed to determine if Goose can replace expensive alternatives like Claude Code.
Have you tried running a coding-focused LLM locally with tools like Goose, Ollama, or Qwen3-coder? Share your experience in the comments below.
Source: https://www.zdnet.com/article/claude-code-alternative-free-local-open-source-goose-getting-started