TEST #649 RESULTS
04/09/2025 - 6:46 PM
ACCELERATOR
MODEL
3.0
tokens/s
generation
3.11
sec
time to first token
496
tokens/s
prompt
78
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
31.6GB
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
650
tokens/s
3.3
tokens/s
1.88
sec
pp4096+tg256
392
tokens/s
1.0
tokens/s
11.46
sec
pp2048+tg256
516
tokens/s
2.1
tokens/s
4.50
sec
pp2048+tg768
518
tokens/s
2.0
tokens/s
4.48
sec
pp1024+tg1024
632
tokens/s
2.9
tokens/s
1.94
sec
pp1280+tg3072
591
tokens/s
1.7
tokens/s
2.53
sec
pp384+tg1152
657
tokens/s
4.0
tokens/s
753
ms
pp64+tg1024
371
tokens/s
5.6
tokens/s
273
ms
pp16+tg1536
132
tokens/s
4.6
tokens/s
203
ms