TEST #1358 RESULTS
08/11/2025 - 11:33 PM
ACCELERATOR
MODEL
21.3
tokens/s
generation
1.70
sec
time to first token
827
tokens/s
prompt
218
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi 4 - Q2_K - Medium
SYSTEM
CPU
13th Gen Intel Core i9-13950HX (alderlake)
RAM
63.8GB
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
877
tokens/s
21.2
tokens/s
1.20
sec
pp4096+tg256
738
tokens/s
20.4
tokens/s
5.61
sec
pp2048+tg256
825
tokens/s
20.2
tokens/s
2.54
sec
pp2048+tg768
832
tokens/s
20.8
tokens/s
2.54
sec
pp1024+tg1024
890
tokens/s
20.7
tokens/s
1.19
sec
pp1280+tg3072
869
tokens/s
21.9
tokens/s
1.52
sec
pp384+tg1152
1007
tokens/s
22.3
tokens/s
463
ms
pp64+tg1024
1045
tokens/s
21.7
tokens/s
102
ms
pp16+tg1536
360
tokens/s
22.3
tokens/s
90
ms