TEST #3250 RESULTS
04/07/2026 - 10:55 AM
ACCELERATOR
MODEL
6.7
tokens/s
generation
38.25
sec
time to first token
35
tokens/s
prompt
18
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 270K Plus (arrowlake-s)
RAM
63.4GB
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
38
tokens/s
7.2
tokens/s
27.19
sec
pp4096+tg256
34
tokens/s
6.3
tokens/s
121.08
sec
pp2048+tg256
37
tokens/s
6.8
tokens/s
56.21
sec
pp2048+tg768
34
tokens/s
6.5
tokens/s
60.47
sec
pp1024+tg1024
35
tokens/s
6.7
tokens/s
29.28
sec
pp1280+tg3072
35
tokens/s
6.4
tokens/s
36.65
sec
pp384+tg1152
36
tokens/s
6.8
tokens/s
10.87
sec
pp64+tg1024
36
tokens/s
6.9
tokens/s
1.92
sec
pp16+tg1536
33
tokens/s
6.9
tokens/s
621
ms