TEST #1038 RESULTS
06/12/2025 - 9:46 PM
ACCELERATOR
MODEL
27.1
tokens/s
generation
1.63
sec
time to first token
798
tokens/s
prompt
237
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
923
tokens/s
27.4
tokens/s
1.15
sec
pp4096+tg256
767
tokens/s
24.7
tokens/s
5.38
sec
pp2048+tg256
856
tokens/s
27.0
tokens/s
2.43
sec
pp2048+tg768
853
tokens/s
26.8
tokens/s
2.44
sec
pp1024+tg1024
933
tokens/s
28.1
tokens/s
1.13
sec
pp1280+tg3072
889
tokens/s
26.2
tokens/s
1.48
sec
pp384+tg1152
948
tokens/s
28.0
tokens/s
444
ms
pp64+tg1024
727
tokens/s
28.0
tokens/s
137
ms
pp16+tg1536
286
tokens/s
28.2
tokens/s
90
ms