TEST #1207 RESULTS
07/10/2025 - 9:54 PM
ACCELERATOR
MODEL
26.9
tokens/s
generation
1.62
sec
time to first token
791
tokens/s
prompt
236
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
944
tokens/s
28.3
tokens/s
1.12
sec
pp4096+tg256
772
tokens/s
24.4
tokens/s
5.35
sec
pp2048+tg256
868
tokens/s
26.9
tokens/s
2.40
sec
pp2048+tg768
859
tokens/s
25.9
tokens/s
2.42
sec
pp1024+tg1024
893
tokens/s
27.2
tokens/s
1.18
sec
pp1280+tg3072
899
tokens/s
25.4
tokens/s
1.46
sec
pp384+tg1152
959
tokens/s
28.0
tokens/s
436
ms
pp64+tg1024
689
tokens/s
28.0
tokens/s
154
ms
pp16+tg1536
232
tokens/s
28.0
tokens/s
105
ms