TEST #1175 RESULTS
07/02/2025 - 8:49 PM
ACCELERATOR
MODEL
2.0
tokens/s
generation
11.20
sec
time to first token
121
tokens/s
prompt
28
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi3 - F16
SYSTEM
CPU
AMD Ryzen 5 7640U w/ Radeon 760M Graphics (znver4)
RAM
30.7GB
OS
Linux
Kernel Release
6.12.10-76061203-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202412060638~1748542656~22.04~663e4dc SMP PREEMPT_DYNAMIC Thu M
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
116
tokens/s
2.3
tokens/s
9.36
sec
pp4096+tg256
107
tokens/s
0.5
tokens/s
40.00
sec
pp2048+tg256
139
tokens/s
1.6
tokens/s
15.37
sec
pp2048+tg768
136
tokens/s
1.5
tokens/s
15.68
sec
pp1024+tg1024
150
tokens/s
2.1
tokens/s
7.23
sec
pp1280+tg3072
153
tokens/s
1.3
tokens/s
8.80
sec
pp384+tg1152
166
tokens/s
2.6
tokens/s
2.59
sec
pp64+tg1024
96
tokens/s
3.2
tokens/s
899
ms
pp16+tg1536
26
tokens/s
2.9
tokens/s
830
ms