Applied AI·Local and self-hosted inference
you download the weight file the Python ecosystem uses and convert it to GGUF, essentially never the other way round.
Safetensors
Draft summary, pending review
The standard weight format of the Python and GPU ecosystem (Hugging Face, vLLM, training code): safe to load, memory-mappable, but weights only, without bundled tokeniser. You will convert from safetensors to GGUF, rarely the reverse.