TEST #500 RESULTS
04/07/2025 - 3:40 PM
ACCELERATOR
MODEL
26.0
tokens/s
generation
1.61
sec
time to first token
803
tokens/s
prompt
235
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
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
941
tokens/s
27.4
tokens/s
1.12
sec
pp4096+tg256
773
tokens/s
23.5
tokens/s
5.34
sec
pp2048+tg256
873
tokens/s
25.8
tokens/s
2.39
sec
pp2048+tg768
868
tokens/s
25.5
tokens/s
2.40
sec
pp1024+tg1024
930
tokens/s
26.8
tokens/s
1.14
sec
pp1280+tg3072
904
tokens/s
25.0
tokens/s
1.45
sec
pp384+tg1152
967
tokens/s
26.9
tokens/s
434
ms
pp64+tg1024
733
tokens/s
25.9
tokens/s
143
ms
pp16+tg1536
235
tokens/s
27.0
tokens/s
106
ms