TEST #769 RESULTS
04/26/2025 - 3:53 AM
ACCELERATOR
MODEL
13.3
tokens/s
generation
2.76
sec
time to first token
450
tokens/s
prompt
130
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU @ 2.00GHz (skylake-avx512)
RAM
31.4GB
OS
Linux
Kernel Release
6.6.56+
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Nov 10 10:07:59 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
574
tokens/s
18.5
tokens/s
1.83
sec
pp4096+tg256
482
tokens/s
13.0
tokens/s
8.60
sec
pp2048+tg256
516
tokens/s
14.8
tokens/s
4.03
sec
pp2048+tg768
498
tokens/s
12.7
tokens/s
4.17
sec
pp1024+tg1024
481
tokens/s
12.1
tokens/s
2.20
sec
pp1280+tg3072
482
tokens/s
11.9
tokens/s
2.72
sec
pp384+tg1152
482
tokens/s
12.3
tokens/s
859
ms
pp64+tg1024
417
tokens/s
12.3
tokens/s
215
ms
pp16+tg1536
118
tokens/s
12.2
tokens/s
204
ms