TEST #518 RESULTS
04/07/2025 - 8:00 PM
ACCELERATOR
MODEL
52.1
tokens/s
generation
488
ms
time to first token
2665
tokens/s
prompt
658
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14600K (alderlake)
RAM
63.8GB
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
3356
tokens/s
53.5
tokens/s
325
ms
pp4096+tg256
2506
tokens/s
48.3
tokens/s
1.66
sec
pp2048+tg256
2995
tokens/s
51.4
tokens/s
704
ms
pp2048+tg768
2988
tokens/s
51.3
tokens/s
705
ms
pp1024+tg1024
3300
tokens/s
52.7
tokens/s
329
ms
pp1280+tg3072
3240
tokens/s
50.3
tokens/s
414
ms
pp384+tg1152
3481
tokens/s
53.5
tokens/s
147
ms
pp64+tg1024
1648
tokens/s
54.4
tokens/s
58
ms
pp16+tg1536
472
tokens/s
53.9
tokens/s
52
ms