TEST #1025 RESULTS
06/10/2025 - 12:02 AM
ACCELERATOR
MODEL
24.2
tokens/s
generation
2.57
sec
time to first token
574
tokens/s
prompt
176
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5800X3D 8-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
681
tokens/s
28.8
tokens/s
1.54
sec
pp4096+tg256
422
tokens/s
12.9
tokens/s
9.78
sec
pp2048+tg256
561
tokens/s
21.5
tokens/s
3.69
sec
pp2048+tg768
560
tokens/s
20.1
tokens/s
3.70
sec
pp1024+tg1024
662
tokens/s
24.6
tokens/s
1.58
sec
pp1280+tg3072
644
tokens/s
17.8
tokens/s
2.03
sec
pp384+tg1152
749
tokens/s
28.8
tokens/s
543
ms
pp64+tg1024
553
tokens/s
32.7
tokens/s
142
ms
pp16+tg1536
340
tokens/s
30.8
tokens/s
72
ms