TEST #1993 RESULTS
12/20/2025 - 5:38 PM
ACCELERATOR
MODEL
55.2
tokens/s
generation
693
ms
time to first token
1728
tokens/s
prompt
516
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-8700 CPU @ 3.20GHz (skylake)
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
1991
tokens/s
57.1
tokens/s
532
ms
pp4096+tg256
1953
tokens/s
50.1
tokens/s
2.12
sec
pp2048+tg256
2083
tokens/s
54.5
tokens/s
1.00
sec
pp2048+tg768
2064
tokens/s
53.9
tokens/s
1.01
sec
pp1024+tg1024
2021
tokens/s
55.8
tokens/s
527
ms
pp1280+tg3072
2040
tokens/s
52.8
tokens/s
647
ms
pp384+tg1152
1852
tokens/s
57.1
tokens/s
252
ms
pp64+tg1024
1227
tokens/s
58.1
tokens/s
69
ms
pp16+tg1536
316
tokens/s
57.6
tokens/s
67
ms