TEST #1440 RESULTS
08/28/2025 - 1:42 PM
ACCELERATOR
MODEL
28.6
tokens/s
generation
935
ms
time to first token
1426
tokens/s
prompt
352
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 265 (arrowlake-s)
RAM
31.5GB
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
1721
tokens/s
29.1
tokens/s
629
ms
pp4096+tg256
1308
tokens/s
27.4
tokens/s
3.17
sec
pp2048+tg256
1548
tokens/s
29.0
tokens/s
1.36
sec
pp2048+tg768
1534
tokens/s
26.3
tokens/s
1.38
sec
pp1024+tg1024
1692
tokens/s
29.2
tokens/s
639
ms
pp1280+tg3072
1623
tokens/s
28.3
tokens/s
826
ms
pp384+tg1152
1847
tokens/s
29.3
tokens/s
243
ms
pp64+tg1024
1190
tokens/s
29.5
tokens/s
102
ms
pp16+tg1536
368
tokens/s
29.4
tokens/s
77
ms