TEST #1489 RESULTS
09/05/2025 - 2:41 PM
ACCELERATOR
MODEL
2.1
tokens/s
generation
14.47
sec
time to first token
230
tokens/s
prompt
32
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 265H (arrowlake)
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
83
tokens/s
2.5
tokens/s
12.81
sec
pp4096+tg256
44
tokens/s
1.5
tokens/s
94.56
sec
pp2048+tg256
395
tokens/s
2.7
tokens/s
5.56
sec
pp2048+tg768
388
tokens/s
2.5
tokens/s
5.69
sec
pp1024+tg1024
377
tokens/s
2.5
tokens/s
3.12
sec
pp1280+tg3072
298
tokens/s
1.8
tokens/s
4.86
sec
pp384+tg1152
292
tokens/s
1.8
tokens/s
1.87
sec
pp64+tg1024
148
tokens/s
2.0
tokens/s
946
ms
pp16+tg1536
46
tokens/s
2.1
tokens/s
818
ms