Update README.md

README.md

@@ -42,7 +42,7 @@ widget:
 - example workflow ([safetensors](https://huggingface.co/calcuis/mochi/blob/main/workflow-mochi-safetensors.json))
 
 ### **review**
-- revised workflow to bypass oom issue and 50% faster with new fp8_e4m3fn file
+- revised workflow to bypass oom issue and around 50% faster with the new fp8_e4m3fn file
 - t5xxl gguf works fine as text encoder
 - mochi gguf file might not work; if so, please wait for the code update