TEST #2497 RESULTS
02/01/2026 - 10:51 AM
ACCELERATOR
MODEL
643
tokens/s
generation
16
ms
time to first token
101046
tokens/s
prompt
16033
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
120894
tokens/s
664
tokens/s
10
ms
pp4096+tg256
86540
tokens/s
590
tokens/s
50
ms
pp2048+tg256
133981
tokens/s
630
tokens/s
17
ms
pp2048+tg768
142904
tokens/s
628
tokens/s
16
ms
pp1024+tg1024
153119
tokens/s
628
tokens/s
8
ms
pp1280+tg3072
139379
tokens/s
641
tokens/s
11
ms
pp384+tg1152
110765
tokens/s
649
tokens/s
20
ms
pp64+tg1024
16454
tokens/s
690
tokens/s
5
ms
pp16+tg1536
5375
tokens/s
665
tokens/s
5
ms