TEST #3900 RESULTS
07/14/2026 - 5:30 AM
ACCELERATOR
MODEL
5.0
tokens/s
generation
43.65
sec
time to first token
31
tokens/s
prompt
15
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 285HX (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
33
tokens/s
5.1
tokens/s
31.55
sec
pp4096+tg256
29
tokens/s
4.6
tokens/s
140.04
sec
pp2048+tg256
32
tokens/s
5.0
tokens/s
64.33
sec
pp2048+tg768
31
tokens/s
5.0
tokens/s
67.31
sec
pp1024+tg1024
31
tokens/s
5.1
tokens/s
32.92
sec
pp1280+tg3072
31
tokens/s
4.9
tokens/s
41.78
sec
pp384+tg1152
32
tokens/s
5.2
tokens/s
12.05
sec
pp64+tg1024
33
tokens/s
5.3
tokens/s
2.15
sec
pp16+tg1536
30
tokens/s
5.2
tokens/s
728
ms