GGUF
Also known as: GGML successor
A single-file container format for quantized models popular in local inference stacks; useful for packaging SLMs for edge or on-prem runtimes that support compatible loaders.
Also known as: GGML successor
A single-file container format for quantized models popular in local inference stacks; useful for packaging SLMs for edge or on-prem runtimes that support compatible loaders.
Contact if you need a term added for a security or procurement review.