TEST #1890 RESULTS
11/30/2025 - 11:30 AM
ACCELERATOR
MODEL
13.5
tokens/s
generation
768
ms
time to first token
1747
tokens/s
prompt
313
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
2305
tokens/s
14.1
tokens/s
514
ms
pp4096+tg256
1655
tokens/s
12.8
tokens/s
2.56
sec
pp2048+tg256
2127
tokens/s
13.5
tokens/s
1.04
sec
pp2048+tg768
2145
tokens/s
13.5
tokens/s
1.03
sec
pp1024+tg1024
2332
tokens/s
13.8
tokens/s
508
ms
pp1280+tg3072
2115
tokens/s
12.8
tokens/s
679
ms
pp384+tg1152
2208
tokens/s
14.0
tokens/s
253
ms
pp64+tg1024
665
tokens/s
13.7
tokens/s
166
ms
pp16+tg1536
174
tokens/s
13.7
tokens/s
172
ms