TEST #3410 RESULTS
04/28/2026 - 9:57 PM
ACCELERATOR
MODEL
6.0
tokens/s
generation
36.07
sec
time to first token
39
tokens/s
prompt
19
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 285K (arrowlake-s)
RAM
127.4GB
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
39
tokens/s
6.3
tokens/s
26.35
sec
pp4096+tg256
34
tokens/s
5.3
tokens/s
120.64
sec
pp2048+tg256
39
tokens/s
6.1
tokens/s
52.74
sec
pp2048+tg768
38
tokens/s
5.7
tokens/s
54.70
sec
pp1024+tg1024
39
tokens/s
6.1
tokens/s
26.37
sec
pp1280+tg3072
40
tokens/s
5.7
tokens/s
32.38
sec
pp384+tg1152
43
tokens/s
6.3
tokens/s
9.06
sec
pp64+tg1024
40
tokens/s
6.3
tokens/s
1.75
sec
pp16+tg1536
37
tokens/s
6.4
tokens/s
608
ms