TEST #2059 RESULTS
12/28/2025 - 8:21 PM
ACCELERATOR
MODEL
12.2
tokens/s
generation
925
ms
time to first token
1420
tokens/s
prompt
266
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7900X 12-Core Processor (znver4)
RAM
63.2GB
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
1895
tokens/s
13.9
tokens/s
628
ms
pp4096+tg256
1434
tokens/s
10.4
tokens/s
2.97
sec
pp2048+tg256
1698
tokens/s
11.3
tokens/s
1.28
sec
pp2048+tg768
1693
tokens/s
11.1
tokens/s
1.28
sec
pp1024+tg1024
1839
tokens/s
11.4
tokens/s
658
ms
pp1280+tg3072
1753
tokens/s
11.0
tokens/s
797
ms
pp384+tg1152
1706
tokens/s
11.5
tokens/s
351
ms
pp64+tg1024
575
tokens/s
13.4
tokens/s
200
ms
pp16+tg1536
189
tokens/s
15.9
tokens/s
157
ms