TEST #1478 RESULTS
09/05/2025 - 12:56 AM
ACCELERATOR
MODEL
5.3
tokens/s
generation
7.87
sec
time to first token
324
tokens/s
prompt
60
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3700X 8-Core Processor (znver2)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
141
tokens/s
5.1
tokens/s
7.46
sec
pp4096+tg256
87
tokens/s
1.7
tokens/s
47.46
sec
pp2048+tg256
503
tokens/s
5.9
tokens/s
4.24
sec
pp2048+tg768
482
tokens/s
5.6
tokens/s
4.43
sec
pp1024+tg1024
504
tokens/s
5.8
tokens/s
2.20
sec
pp1280+tg3072
422
tokens/s
4.8
tokens/s
3.23
sec
pp384+tg1152
430
tokens/s
6.0
tokens/s
1.09
sec
pp64+tg1024
265
tokens/s
6.4
tokens/s
401
ms
pp16+tg1536
78
tokens/s
6.4
tokens/s
360
ms