TEST #3555 RESULTS
05/16/2026 - 3:39 PM
ACCELERATOR
MODEL
40.5
tokens/s
generation
866
ms
time to first token
1550
tokens/s
prompt
417
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
31.4GB
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
1761
tokens/s
41.2
tokens/s
605
ms
pp4096+tg256
1388
tokens/s
38.1
tokens/s
2.98
sec
pp2048+tg256
1633
tokens/s
38.8
tokens/s
1.28
sec
pp2048+tg768
1661
tokens/s
41.1
tokens/s
1.26
sec
pp1024+tg1024
1870
tokens/s
41.7
tokens/s
572
ms
pp1280+tg3072
1777
tokens/s
38.9
tokens/s
746
ms
pp384+tg1152
2143
tokens/s
41.7
tokens/s
219
ms
pp64+tg1024
1259
tokens/s
41.4
tokens/s
74
ms
pp16+tg1536
457
tokens/s
41.4
tokens/s
57
ms