TEST #582 RESULTS
04/08/2025 - 10:42 AM
ACCELERATOR
MODEL
24.5
tokens/s
generation
2.40
sec
time to first token
612
tokens/s
prompt
184
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
733
tokens/s
28.9
tokens/s
1.43
sec
pp4096+tg256
446
tokens/s
13.4
tokens/s
9.25
sec
pp2048+tg256
604
tokens/s
21.6
tokens/s
3.43
sec
pp2048+tg768
606
tokens/s
20.2
tokens/s
3.43
sec
pp1024+tg1024
724
tokens/s
24.8
tokens/s
1.45
sec
pp1280+tg3072
701
tokens/s
17.9
tokens/s
1.86
sec
pp384+tg1152
805
tokens/s
29.1
tokens/s
506
ms
pp64+tg1024
551
tokens/s
33.1
tokens/s
143
ms
pp16+tg1536
340
tokens/s
31.3
tokens/s
72
ms