TEST #895 RESULTS
05/17/2025 - 4:33 AM
ACCELERATOR
MODEL
28.4
tokens/s
generation
1.52
sec
time to first token
779
tokens/s
prompt
244
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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1158
tokens/s
32.6
tokens/s
915
ms
pp4096+tg256
947
tokens/s
28.2
tokens/s
4.36
sec
pp2048+tg256
882
tokens/s
30.1
tokens/s
2.35
sec
pp2048+tg768
881
tokens/s
28.9
tokens/s
2.36
sec
pp1024+tg1024
816
tokens/s
29.4
tokens/s
1.29
sec
pp1280+tg3072
824
tokens/s
26.7
tokens/s
1.58
sec
pp384+tg1152
740
tokens/s
26.6
tokens/s
557
ms
pp64+tg1024
575
tokens/s
26.3
tokens/s
156
ms
pp16+tg1536
187
tokens/s
26.8
tokens/s
138
ms