TEST #632 RESULTS
04/09/2025 - 8:37 AM
ACCELERATOR
MODEL
32.8
tokens/s
generation
968
ms
time to first token
1337
tokens/s
prompt
356
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i9-13980HX (alderlake)
RAM
191.7GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1598
tokens/s
33.9
tokens/s
671
ms
pp4096+tg256
1261
tokens/s
32.0
tokens/s
3.28
sec
pp2048+tg256
1517
tokens/s
33.8
tokens/s
1.38
sec
pp2048+tg768
1512
tokens/s
32.7
tokens/s
1.39
sec
pp1024+tg1024
1644
tokens/s
32.1
tokens/s
653
ms
pp1280+tg3072
1487
tokens/s
31.6
tokens/s
893
ms
pp384+tg1152
1654
tokens/s
32.6
tokens/s
264
ms
pp64+tg1024
995
tokens/s
33.3
tokens/s
115
ms
pp16+tg1536
360
tokens/s
33.0
tokens/s
75
ms