AlexanderNyr/AuraLite-AI
Train and fine-tune LLMs on an old PC without a GPU. AuraLite Studio (Windows app, no Python) picks a model for your computer, fine-tunes Qwen3.5 with LoRA/QLoRA on the CPU, trains small models from scratch and exports GGUF for Ollama and LM Studio. English and Russian UI.
GitHub repository with 6 stars and 1 forks.
Language: Python
Topics: llm, pytorch, cpu-training, desktop-app, fine-tuning, gguf, llama-cpp, lm-studio, local-llm, lora