TEST #472 RESULTS
04/07/2025 - 4:42 AM
ACCELERATOR
MODEL
5.1
tokens/s
generation
8.07
sec
time to first token
376
tokens/s
prompt
62
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-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
143
tokens/s
4.8
tokens/s
7.38
sec
pp4096+tg256
80
tokens/s
2.1
tokens/s
51.49
sec
pp2048+tg256
585
tokens/s
5.7
tokens/s
3.68
sec
pp2048+tg768
570
tokens/s
5.5
tokens/s
3.78
sec
pp1024+tg1024
600
tokens/s
5.7
tokens/s
1.88
sec
pp1280+tg3072
500
tokens/s
4.6
tokens/s
2.78
sec
pp384+tg1152
523
tokens/s
5.6
tokens/s
912
ms
pp64+tg1024
306
tokens/s
5.8
tokens/s
390
ms
pp16+tg1536
78
tokens/s
6.0
tokens/s
374
ms