TEST #1967 RESULTS
12/19/2025 - 6:26 PM
ACCELERATOR
MODEL
22.2
tokens/s
generation
2.18
sec
time to first token
589
tokens/s
prompt
182
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600GT with Radeon Graphics (znver3)
RAM
31.8GB
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
687
tokens/s
25.1
tokens/s
1.53
sec
pp4096+tg256
578
tokens/s
16.1
tokens/s
7.17
sec
pp2048+tg256
642
tokens/s
20.5
tokens/s
3.23
sec
pp2048+tg768
641
tokens/s
19.7
tokens/s
3.24
sec
pp1024+tg1024
678
tokens/s
23.9
tokens/s
1.55
sec
pp1280+tg3072
668
tokens/s
19.1
tokens/s
1.96
sec
pp384+tg1152
629
tokens/s
25.3
tokens/s
648
ms
pp64+tg1024
586
tokens/s
25.8
tokens/s
146
ms
pp16+tg1536
193
tokens/s
24.4
tokens/s
123
ms