Update README.md

README.md

@@ -90,8 +90,8 @@ The plot below showcases performance normalized between the negative control (ra
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f2bd3bdb7cbd214b658c48/dcvZhbtR_fJ6KSFYgI6l6.png)
 
 ## Inference speeds
-We look at various ESM models and their throughput on an H100. Adding efficient batching between ESMC and ESM++ significantly improves the throughput. ESM++ small is even faster than ESM2-35M with long sequences!
-The most gains will be seen with PyTorch > 2.5 on linux machines.
+We look at various ESM models and their throughput on an H100. Adding efficient batching between ESMC and ESM++ significantly improves the throughput, although ESM++ is also faster than ESMC for batch size one. ESM++ small is even faster than ESM2-35M with long sequences! The most gains will be seen with PyTorch > 2.5 on linux machines.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f2bd3bdb7cbd214b658c48/Lu6nWB9Fc-7YTql3Z1hVB.png)
 
 ### Citation
 If you use any of this implementation or work please cite it (as well as the ESMC preprint). Bibtex for both coming soon.