TEST #3464 RESULTS
05/07/2026 - 5:51 PM
ACCELERATOR
MODEL
14.4
tokens/s
generation
11.22
sec
time to first token
257
tokens/s
prompt
69
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (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
162
tokens/s
11.6
tokens/s
6.39
sec
pp4096+tg256
92
tokens/s
3.0
tokens/s
44.70
sec
pp2048+tg256
130
tokens/s
6.8
tokens/s
15.88
sec
pp2048+tg768
128
tokens/s
5.7
tokens/s
16.15
sec
pp1024+tg1024
159
tokens/s
13.2
tokens/s
6.52
sec
pp1280+tg3072
149
tokens/s
5.1
tokens/s
8.70
sec
pp384+tg1152
169
tokens/s
31.7
tokens/s
2.40
sec
pp64+tg1024
1170
tokens/s
24.3
tokens/s
77
ms
pp16+tg1536
153
tokens/s
28.7
tokens/s
132
ms