GGUF
GGUF (GPT-Generated Unified Format) is the universal single-file format used by local AI tools like Ollama, LM Studio, and llama.cpp to store and run quantized language models.
Before GGUF arrived, running a local model often meant juggling folders full of split files, separate tokenizer configs, and messy settings templates. GGUF bundles everything—the quantized model weights, vocabulary, prompt formatting rules, and metadata—into one tidy, self-contained .gguf file.
Its biggest superpower is cross-platform portability. The exact same .gguf file you download will run natively on an NVIDIA RTX gaming PC, an AMD Radeon workstation, or an Apple Silicon MacBook, and it automatically supports splitting layers between your GPU VRAM and system RAM when memory gets tight.
Looking for verified hardware rigs?
Check our real-time £/GB VRAM index to find systems optimized for local model inference.