TEST #4273 RESULTS
10/12/2026 - 2:36 AM
ACCELERATOR
MODEL
6.7
tokens/s
generation
10.68
sec
time to first token
129
tokens/s
prompt
43
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D2 16-Core Processor
RAM
31.1GB
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
140
tokens/s
6.8
tokens/s
7.44
sec
pp4096+tg256
112
tokens/s
6.2
tokens/s
36.71
sec
pp2048+tg256
131
tokens/s
6.6
tokens/s
15.80
sec
pp2048+tg768
131
tokens/s
6.6
tokens/s
15.79
sec
pp1024+tg1024
142
tokens/s
6.7
tokens/s
7.34
sec
pp1280+tg3072
140
tokens/s
6.5
tokens/s
9.27
sec
pp384+tg1152
144
tokens/s
6.8
tokens/s
2.80
sec
pp64+tg1024
130
tokens/s
6.9
tokens/s
635
ms
pp16+tg1536
89
tokens/s
6.9
tokens/s
321
ms