TEST #3249 RESULTS
04/07/2026 - 8:15 AM
ACCELERATOR
MODEL
9.5
tokens/s
generation
2.31
sec
time to first token
547
tokens/s
prompt
131
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 7600X 6-Core Processor (znver4)
RAM
31.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
643
tokens/s
10.2
tokens/s
1.69
sec
pp4096+tg256
578
tokens/s
7.6
tokens/s
7.21
sec
pp2048+tg256
626
tokens/s
9.9
tokens/s
3.37
sec
pp2048+tg768
634
tokens/s
9.3
tokens/s
3.33
sec
pp1024+tg1024
606
tokens/s
9.3
tokens/s
1.80
sec
pp1280+tg3072
613
tokens/s
9.2
tokens/s
2.18
sec
pp384+tg1152
709
tokens/s
10.1
tokens/s
670
ms
pp64+tg1024
398
tokens/s
10.0
tokens/s
275
ms
pp16+tg1536
119
tokens/s
10.0
tokens/s
232
ms