TEST #707 RESULTS
04/13/2025 - 7:42 PM
ACCELERATOR
MODEL
145
tokens/s
generation
231
ms
time to first token
5535
tokens/s
prompt
1515
LocalScore
HOW YOU STACK UP
Explore All ResultsPhi 4 Mini Instruct - Q4_K - Medium
SYSTEM
CPU
AMD EPYC 7352 24-Core Processor (znver2)
RAM
125.6GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Mar 19 17:07:41 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6773
tokens/s
150
tokens/s
158
ms
pp4096+tg256
5479
tokens/s
127
tokens/s
756
ms
pp2048+tg256
6288
tokens/s
143
tokens/s
333
ms
pp2048+tg768
6285
tokens/s
139
tokens/s
333
ms
pp1024+tg1024
6768
tokens/s
147
tokens/s
158
ms
pp1280+tg3072
6551
tokens/s
136
tokens/s
202
ms
pp384+tg1152
6923
tokens/s
153
tokens/s
72
ms
pp64+tg1024
3967
tokens/s
157
tokens/s
42
ms
pp16+tg1536
785
tokens/s
156
tokens/s
27
ms