TEST #1671 RESULTS
10/18/2025 - 2:41 PM
ACCELERATOR
MODEL
3.3
tokens/s
generation
2.85
sec
time to first token
550
tokens/s
prompt
86
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7700 8-Core Processor (znver4)
RAM
63.1GB
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
703
tokens/s
3.6
tokens/s
1.74
sec
pp4096+tg256
427
tokens/s
1.1
tokens/s
10.55
sec
pp2048+tg256
567
tokens/s
2.4
tokens/s
4.09
sec
pp2048+tg768
568
tokens/s
2.1
tokens/s
4.09
sec
pp1024+tg1024
701
tokens/s
3.1
tokens/s
1.75
sec
pp1280+tg3072
648
tokens/s
1.8
tokens/s
2.31
sec
pp384+tg1152
741
tokens/s
4.4
tokens/s
675
ms
pp64+tg1024
433
tokens/s
6.2
tokens/s
239
ms
pp16+tg1536
160
tokens/s
5.1
tokens/s
176
ms