Silan10
/

flux_quantized_half

Model card Files Files and versions

Silan10 commited on Nov 20, 2025

Commit

fc26347

·

verified ·

1 Parent(s): 462e3fb

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -14,7 +14,8 @@ pipeline_tag: text-to-image
 text-to-image model.
 This repository only changes the **numerical precision of the weights** to
-`torch.float16` using PyTorch.
 ## Usage

 text-to-image model.
 This repository only changes the **numerical precision of the weights** to
+`torch.float16` using PyTorch. This is not real quantization (like int8/int4). Still,
+converting the model to float16 saves the memory, reduces RAM usage and speeds up loading times.
 ## Usage