TEST #3450 RESULTS
05/05/2026 - 7:40 PM
ACCELERATOR
MODEL
2.7
tokens/s
generation
69.82
sec
time to first token
20
tokens/s
prompt
9
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i9-9900K CPU @ 3.60GHz (skylake)
RAM
31.9GB
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
18
tokens/s
2.7
tokens/s
57.81
sec
pp4096+tg256
17
tokens/s
2.4
tokens/s
235.64
sec
pp2048+tg256
20
tokens/s
2.7
tokens/s
104.63
sec
pp2048+tg768
21
tokens/s
2.8
tokens/s
100.13
sec
pp1024+tg1024
21
tokens/s
2.9
tokens/s
48.20
sec
pp1280+tg3072
21
tokens/s
2.7
tokens/s
61.31
sec
pp384+tg1152
25
tokens/s
2.9
tokens/s
15.58
sec
pp64+tg1024
19
tokens/s
2.9
tokens/s
3.69
sec
pp16+tg1536
15
tokens/s
2.8
tokens/s
1.38
sec