TEST #3992 RESULTS
08/05/2026 - 2:02 AM
MODEL
6.5
tokens/s
generation
76.57
sec
time to first token
18
tokens/s
prompt
12
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
11.8GB
OS
Linux
Kernel Release
6.18.15
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #1 SMP Tue Mar 17 01:36:53 UTC 2026
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
19
tokens/s
7.2
tokens/s
55.09
sec
pp4096+tg256
17
tokens/s
5.8
tokens/s
247.78
sec
pp2048+tg256
17
tokens/s
6.6
tokens/s
117.67
sec
pp2048+tg768
18
tokens/s
6.5
tokens/s
116.72
sec
pp1024+tg1024
18
tokens/s
6.4
tokens/s
57.18
sec
pp1280+tg3072
18
tokens/s
6.7
tokens/s
70.44
sec
pp384+tg1152
19
tokens/s
6.7
tokens/s
20.21
sec
pp64+tg1024
22
tokens/s
7.2
tokens/s
3.01
sec
pp16+tg1536
18
tokens/s
5.3
tokens/s
1.01
sec