TEST #2090 RESULTS
01/03/2026 - 11:39 PM
ACCELERATOR
MODEL
1.1
tokens/s
generation
24.98
sec
time to first token
83
tokens/s
prompt
15
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
RAM
15.8GB
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
46
tokens/s
1.2
tokens/s
22.89
sec
pp4096+tg256
30
tokens/s
0.7
tokens/s
136.77
sec
pp2048+tg256
127
tokens/s
1.1
tokens/s
17.05
sec
pp2048+tg768
120
tokens/s
1.0
tokens/s
18.17
sec
pp1024+tg1024
121
tokens/s
1.2
tokens/s
9.45
sec
pp1280+tg3072
112
tokens/s
1.1
tokens/s
12.31
sec
pp384+tg1152
116
tokens/s
1.2
tokens/s
4.21
sec
pp64+tg1024
60
tokens/s
1.2
tokens/s
1.97
sec
pp16+tg1536
14
tokens/s
1.2
tokens/s
1.96
sec