Skip to content

Commit 2a33116

Browse files
kimishpatelfacebook-github-bot
authored andcommitted
Update benchmarking numbers
Summary: ATT Created from CodeHub with https://fburl.com/edit-in-codehub Reviewed By: lucylq Differential Revision: D55817614
1 parent 1adf268 commit 2a33116

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

examples/models/llama2/README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -36,9 +36,9 @@ Performance was measured on Samsung Galaxy S22, S23, S24 and One Plus 12. Measur
3636

3737
|Device | Groupwise 4-bit (128) | Groupwise 4-bit (256)
3838
|--------| ---------------------- | ---------------
39-
|Galaxy S22 | x | x |
40-
|Galaxy S24 | x | x |
41-
|One plus 12 | x | x |
39+
|Galaxy S22 | 8.15 tokens/second | 8.3 tokens/second |
40+
|Galaxy S24 | 10.66 tokens/second | 11.26 tokens/second |
41+
|One plus 12 | 11.55 tokens/second | 11.6 tokens/second |
4242
|iPhone 15 pro | x | x |
4343

4444

0 commit comments

Comments
 (0)