TEST #1269 RESULTS
07/29/2025 - 10:39 PM
ACCELERATOR
MODEL
7.9
tokens/s
generation
4.77
sec
time to first token
302
tokens/s
prompt
80
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12800H (alderlake)
RAM
63.7GB
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
751
tokens/s
25.4
tokens/s
1.40
sec
pp4096+tg256
693
tokens/s
12.5
tokens/s
5.97
sec
pp2048+tg256
313
tokens/s
6.5
tokens/s
6.66
sec
pp2048+tg768
190
tokens/s
4.3
tokens/s
10.95
sec
pp1024+tg1024
187
tokens/s
4.2
tokens/s
5.66
sec
pp1280+tg3072
140
tokens/s
4.6
tokens/s
9.37
sec
pp384+tg1152
201
tokens/s
4.5
tokens/s
2.14
sec
pp64+tg1024
170
tokens/s
4.6
tokens/s
503
ms
pp16+tg1536
74
tokens/s
4.9
tokens/s
334
ms