TEST #2014 RESULTS
12/21/2025 - 2:19 PM
ACCELERATOR
MODEL
4.5
tokens/s
generation
8.27
sec
time to first token
294
tokens/s
prompt
54
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
31.9GB
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
132
tokens/s
4.2
tokens/s
7.98
sec
pp4096+tg256
85
tokens/s
1.7
tokens/s
48.91
sec
pp2048+tg256
461
tokens/s
4.9
tokens/s
4.65
sec
pp2048+tg768
444
tokens/s
4.7
tokens/s
4.83
sec
pp1024+tg1024
451
tokens/s
4.9
tokens/s
2.48
sec
pp1280+tg3072
401
tokens/s
4.0
tokens/s
3.44
sec
pp384+tg1152
384
tokens/s
5.2
tokens/s
1.24
sec
pp64+tg1024
226
tokens/s
5.4
tokens/s
470
ms
pp16+tg1536
60
tokens/s
5.2
tokens/s
459
ms