TEST #3901 RESULTS
07/14/2026 - 5:30 AM
ACCELERATOR
MODEL
5.0
tokens/s
generation
43.08
sec
time to first token
32
tokens/s
prompt
16
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
127.4GB
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
35
tokens/s
5.2
tokens/s
29.42
sec
pp4096+tg256
30
tokens/s
4.6
tokens/s
136.87
sec
pp2048+tg256
30
tokens/s
5.0
tokens/s
67.43
sec
pp2048+tg768
31
tokens/s
4.9
tokens/s
66.97
sec
pp1024+tg1024
33
tokens/s
5.1
tokens/s
31.64
sec
pp1280+tg3072
32
tokens/s
4.9
tokens/s
40.72
sec
pp384+tg1152
33
tokens/s
5.2
tokens/s
11.97
sec
pp64+tg1024
35
tokens/s
5.1
tokens/s
2.02
sec
pp16+tg1536
32
tokens/s
5.1
tokens/s
691
ms