ggml-org/llama.qtcreator

llama.qtcreator

Local LLM-assisted text completion for Qt Creator.

---

Features

• Auto-suggest on cursor movement. Toggle enable / disable with Ctrl+Shift+G
• Trigger the suggestion manually by pressing Ctrl+G
• Accept a suggestion with Tab
• Accept the first line of a suggestion with Shift+Tab
• Control max text generation time
• Configure scope of context around the cursor
• Ring context with chunks from open and edited files and yanked text
• Supports very large contexts even on low-end hardware via smart context reuse
• Speculative FIM support
• Speculative Decoding support
• Display performance stats
• Chat support
• Source and Image drag & drop support
• Current editor selection predefined and custom LLM prompts
• Tools usage

llama.cpp setup

The plugin requires a llama.cpp server instance to be running at:

Mac OS

brew install llama.cpp

Windows

winget install llama.cpp

Any other OS

Either build from source or use the latest binaries: https://github.com/ggml-org/llama.cpp/releases

llama.cpp settings

Here are recommended settings, depending on the amount of VRAM that you have:

• More than 16GB VRAM:

  llama-server --fim-qwen-7b-default
  

• Less than 16GB VRAM:

  llama-server --fim-qwen-3b-default
  

• Less than 8GB VRAM:

  llama-server --fim-qwen-1.5b-default
  

Use llama-server --help for more details.

Recommended LLMs

The plugin requires FIM-compatible models: HF collection

Examples

A Qt Quick example on MacBook Pro M3 Qwen2.5-Coder 3B Q8_0:

Chat on a Mac Studio M2 with gpt-oss 20B:

Using Tools on a MacBook M3 with gpt-oss 20B:

https://github.com/user-attachments/assets/b38f2d6b-aea8-4879-be17-73f0290e4f71

Implementation details

The plugin aims to be very simple and lightweight and at the same time to provide high-quality and performant local FIM completions, even on consumer-grade hardware.

Other IDEs

• Vim/Neovim: https://github.com/ggml-org/llama.vim
• VS Code: https://github.com/ggml-org/llama.vscode