angelolamonaca / PyTorch-Precision-ConverterView on GitHub
Convert PyTorch checkpoints, safetensors files and whole Hugging Face model folders to fp16, bf16, fp8 or ComfyUI fp8_scaled, int8_convrot and int8, turn FP8 models (DeepSeek, Qwen) back into BF16 on a CPU, merge or split sharded safetensors, and extract EMA weights, with one command and without loading the model into RAM.
☆12Oct 29, 2026Updated this week

Alternatives and similar repositories for PyTorch-Precision-Converter

Users that are interested in PyTorch-Precision-Converter are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?