This repository contains the quantized GGUF versions of Gata 0.01 12B, a specialized model fine-tuned for browser game development and Three.js/TypeScript engineering.
The GGUF files were compiled using the --no-mtp flag for maximum compatibility with vanilla llama.cpp builds.
Available Quantizations
Q4_K_M (q4 km): Excellent balance between size (6.46 GB) and quality. Highly recommended for 24GB or smaller GPUs.
This model is based on the Qwen model family developed by Alibaba Cloud. It inherits the Qwen License Agreement.
Please refer to the Qwen License for usage constraints and commercial application rules.
