TEST #1880 RESULTS
11/28/2025 - 2:15 PM
ACCELERATOR
MODEL
3.5
tokens/s
generation
107.80
sec
time to first token
12
tokens/s
prompt
7
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 185H (alderlake)
RAM
31.4GB
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
13
tokens/s
2.9
tokens/s
76.39
sec
pp4096+tg256
12
tokens/s
2.7
tokens/s
335.48
sec
pp2048+tg256
13
tokens/s
3.7
tokens/s
161.53
sec
pp2048+tg768
14
tokens/s
4.1
tokens/s
151.63
sec
pp1024+tg1024
11
tokens/s
3.8
tokens/s
90.94
sec
pp1280+tg3072
11
tokens/s
3.4
tokens/s
117.18
sec
pp384+tg1152
13
tokens/s
4.3
tokens/s
29.51
sec
pp64+tg1024
11
tokens/s
4.2
tokens/s
5.95
sec
pp16+tg1536
11
tokens/s
2.7
tokens/s
1.63
sec