TEST #337 RESULTS
04/06/2025 - 1:30 AM
ACCELERATOR
MODEL
3.5
tokens/s
generation
7.99
sec
time to first token
327
tokens/s
prompt
52
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
31.6GB
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
136
tokens/s
3.9
tokens/s
7.82
sec
pp4096+tg256
86
tokens/s
2.9
tokens/s
47.96
sec
pp2048+tg256
545
tokens/s
3.6
tokens/s
4.03
sec
pp2048+tg768
527
tokens/s
3.4
tokens/s
4.17
sec
pp1024+tg1024
538
tokens/s
3.6
tokens/s
2.18
sec
pp1280+tg3072
426
tokens/s
3.0
tokens/s
3.33
sec
pp384+tg1152
430
tokens/s
3.7
tokens/s
1.22
sec
pp64+tg1024
205
tokens/s
3.8
tokens/s
578
ms
pp16+tg1536
49
tokens/s
3.6
tokens/s
606
ms