TEST #1902 RESULTS
12/03/2025 - 10:31 AM
ACCELERATOR
MODEL
9.3
tokens/s
generation
34.61
sec
time to first token
39
tokens/s
prompt
22
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 285K (arrowlake-s)
RAM
47.3GB
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
40
tokens/s
10.0
tokens/s
25.74
sec
pp4096+tg256
36
tokens/s
8.8
tokens/s
113.58
sec
pp2048+tg256
39
tokens/s
8.9
tokens/s
52.12
sec
pp2048+tg768
41
tokens/s
8.7
tokens/s
50.21
sec
pp1024+tg1024
40
tokens/s
9.5
tokens/s
25.95
sec
pp1280+tg3072
40
tokens/s
8.9
tokens/s
31.95
sec
pp384+tg1152
40
tokens/s
9.6
tokens/s
9.73
sec
pp64+tg1024
40
tokens/s
9.5
tokens/s
1.68
sec
pp16+tg1536
37
tokens/s
9.3
tokens/s
538
ms