TEST #1891 RESULTS
11/30/2025 - 11:44 AM
ACCELERATOR
MODEL
13.4
tokens/s
generation
756
ms
time to first token
1760
tokens/s
prompt
315
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
63.7GB
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
2351
tokens/s
14.8
tokens/s
501
ms
pp4096+tg256
1759
tokens/s
12.7
tokens/s
2.41
sec
pp2048+tg256
2154
tokens/s
13.9
tokens/s
1.03
sec
pp2048+tg768
2155
tokens/s
13.9
tokens/s
1.03
sec
pp1024+tg1024
2440
tokens/s
14.0
tokens/s
488
ms
pp1280+tg3072
2078
tokens/s
13.4
tokens/s
696
ms
pp384+tg1152
2187
tokens/s
13.2
tokens/s
255
ms
pp64+tg1024
557
tokens/s
11.8
tokens/s
199
ms
pp16+tg1536
155
tokens/s
13.4
tokens/s
196
ms