TEST #1733 RESULTS
11/05/2025 - 5:29 AM
ACCELERATOR
MODEL
5.8
tokens/s
generation
17.68
sec
time to first token
69
tokens/s
prompt
28
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9900X 12-Core Processor
RAM
31.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
98
tokens/s
6.4
tokens/s
10.65
sec
pp4096+tg256
81
tokens/s
5.8
tokens/s
50.55
sec
pp2048+tg256
95
tokens/s
6.2
tokens/s
21.71
sec
pp2048+tg768
95
tokens/s
5.6
tokens/s
21.82
sec
pp1024+tg1024
52
tokens/s
5.7
tokens/s
20.03
sec
pp1280+tg3072
51
tokens/s
5.5
tokens/s
25.11
sec
pp384+tg1152
53
tokens/s
5.8
tokens/s
7.39
sec
pp64+tg1024
53
tokens/s
5.8
tokens/s
1.37
sec
pp16+tg1536
47
tokens/s
5.8
tokens/s
511
ms