TEST #2467 RESULTS
02/01/2026 - 6:07 AM
ACCELERATOR
MODEL
697
tokens/s
generation
15
ms
time to first token
101949
tokens/s
prompt
16827
LocalScore
HOW YOU STACK UP
Explore All ResultsPythia 14m - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
132971
tokens/s
684
tokens/s
9
ms
pp4096+tg256
89184
tokens/s
623
tokens/s
48
ms
pp2048+tg256
127332
tokens/s
698
tokens/s
18
ms
pp2048+tg768
144611
tokens/s
733
tokens/s
16
ms
pp1024+tg1024
141310
tokens/s
728
tokens/s
9
ms
pp1280+tg3072
139958
tokens/s
697
tokens/s
10
ms
pp384+tg1152
117428
tokens/s
721
tokens/s
16
ms
pp64+tg1024
18611
tokens/s
703
tokens/s
5
ms
pp16+tg1536
6133
tokens/s
682
tokens/s
4
ms