Repository files navigation

Llama Coder is a better and self-hosted Github Copilot replacement forVS Code. Llama Coder usesOllama and codellama to provide autocomplete that runs on your hardware. Works best with Mac M1/M2/M3 or with RTX 4090.

VS Code Plugin

• 🚀 As good as Copilot
• ⚡️ Fast. Works well on consumer GPUs. Apple Silicon or RTX 4090 is recommended for best performance.
• 🔐 No telemetry or tracking
• 🔬 Works with any language coding or human one.

Minimum required RAM: 16GB is a minimum, more is better since even smallest model takes 5GB of RAM.The best way: dedicated machine with RTX 4090. InstallOllama on this machine and configure endpoint in extension settings to offload to this machine.Second best way: run on MacBook M1/M2/M3 with enough RAM (more == better, but 10gb extra would be enough).For windows notebooks: it runs good with decent GPU, but dedicated machine with a good GPU is recommended. Perfect if you have a dedicated gaming PC.

InstallOllama on local machine and then launch the extension in VSCode, everything should work as it is.

InstallOllama on dedicated machine and configure endpoint to it in extension settings. Ollama usually uses port 11434 and binds to127.0.0.1, to change it you should setOLLAMA_HOST to0.0.0.0.

Currently Llama Coder supports only Codellama. Model is quantized in different ways, but our tests shows thatq4 is an optimal way to run network. When selecting model the bigger the model is, it performs better. Always pick the model with the biggest size and the biggest possible quantization for your machine. Default one isstable-code:3b-code-q4_0 and should work everywhere and outperforms most other models.

• m - slow on MacOS
• g - slow on older NVidia cards (pre 30xx)

Most of the problems could be seen in output of a plugin in VS Code extension output.

• Ability to pause completition (by @bkyle)
• Bearer token support for remote inference (by @Sinan-Karakaya)

• Fix remote files support

• Remote support
• Fix codellama prompt preparation
• Add trigger delay
• Add jupyter notebooks support

• Added Stable Code model
• Pause download only for specific model instead of all models

• Adding ability to pick a custom model
• Asking user if they want to download model if it is not available

• Adding deepseek 1b model and making it default

• Improved DeepSeek support and language detection

• Added DeepSeek support
• Ability to change temperature and top p
• Fixed some bugs

• Fix ollama links
• Added more models

• Initial release of Llama Coder