GGUF Model Format & Quantization

5 repos

GGUF is a file format for storing and distributing quantized large language and image generation models, enabling efficient inference on consumer hardware. This cluster contains model implementations, conversion utilities, and specialized variants (image generation, image editing, multimodal) packaged in GGUF format, primarily serving the text-to-image and vision-language model communities. Repositories here focus on making state-of-the-art models like Qwen and Stable Diffusion accessible through optimized quantization and streamlined deployment.

Related clusters