Update README.md

README.md

@@ -43,7 +43,7 @@ Measured on T4 (22 GB VRAM) with `torch.bfloat16`, `guidance_scale=0.0`, 9 infer
 | Peak VRAM | 21.35 GB | 16.76 GB | **4.59 GB (22%)** |
 | Generation time | 3.9s | 3.5s | — |
 
-The student+adapter brings peak VRAM from ~21.4 GB down to ~16.8 GB  fitting comfortably on a 22 GB T4 where the original barely fits. The DiT transformer and VAE are unchanged (~12 GB total); all savings come from the text encoder.
+The student+adapter brings peak VRAM from 21.4 GB down to 16.8 GB  fitting comfortably on a 22 GB T4 where the original barely fits. The DiT transformer and VAE are unchanged (12 GB total); all savings come from the text encoder.
 
 ## Quick Start