TEST #1459 RESULTS
08/30/2025 - 9:51 AM
ACCELERATOR
MODEL
28.8
tokens/s
generation
1.28
sec
time to first token
1004
tokens/s
prompt
282
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900HX with Radeon Graphics (znver3)
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
1209
tokens/s
30.6
tokens/s
880
ms
pp4096+tg256
989
tokens/s
26.8
tokens/s
4.18
sec
pp2048+tg256
1091
tokens/s
28.0
tokens/s
1.91
sec
pp2048+tg768
1109
tokens/s
29.0
tokens/s
1.88
sec
pp1024+tg1024
1111
tokens/s
29.5
tokens/s
956
ms
pp1280+tg3072
1138
tokens/s
27.8
tokens/s
1.16
sec
pp384+tg1152
1209
tokens/s
29.2
tokens/s
353
ms
pp64+tg1024
885
tokens/s
29.2
tokens/s
141
ms
pp16+tg1536
291
tokens/s
29.1
tokens/s
90
ms