TEST #2767 RESULTS
02/21/2026 - 1:15 AM
ACCELERATOR
MODEL
62.3
tokens/s
generation
239
ms
time to first token
5328
tokens/s
prompt
1115
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 285K (arrowlake-s)
RAM
63.4GB
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
6888
tokens/s
64.9
tokens/s
165
ms
pp4096+tg256
5423
tokens/s
60.9
tokens/s
771
ms
pp2048+tg256
6291
tokens/s
60.7
tokens/s
342
ms
pp2048+tg768
6294
tokens/s
61.3
tokens/s
342
ms
pp1024+tg1024
6854
tokens/s
62.1
tokens/s
167
ms
pp1280+tg3072
6447
tokens/s
61.5
tokens/s
214
ms
pp384+tg1152
6528
tokens/s
62.7
tokens/s
75
ms
pp64+tg1024
2455
tokens/s
63.5
tokens/s
42
ms
pp16+tg1536
774
tokens/s
63.3
tokens/s
36
ms