TEST #894 RESULTS
05/17/2025 - 3:38 AM
ACCELERATOR
MODEL
27.4
tokens/s
generation
1.58
sec
time to first token
793
tokens/s
prompt
240
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
1186
tokens/s
31.5
tokens/s
895
ms
pp4096+tg256
812
tokens/s
27.4
tokens/s
5.09
sec
pp2048+tg256
969
tokens/s
30.1
tokens/s
2.15
sec
pp2048+tg768
845
tokens/s
24.6
tokens/s
2.45
sec
pp1024+tg1024
797
tokens/s
25.8
tokens/s
1.32
sec
pp1280+tg3072
818
tokens/s
27.0
tokens/s
1.60
sec
pp384+tg1152
900
tokens/s
27.8
tokens/s
460
ms
pp64+tg1024
575
tokens/s
26.5
tokens/s
155
ms
pp16+tg1536
232
tokens/s
26.2
tokens/s
106
ms