TEST #225 RESULTS
04/04/2025 - 4:24 AM
ACCELERATOR
MODEL
182
tokens/s
generation
169
ms
time to first token
8050
tokens/s
prompt
2055
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600 6-Core Processor (znver3)
RAM
63.9GB
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
10108
tokens/s
204
tokens/s
106
ms
pp4096+tg256
6957
tokens/s
167
tokens/s
594
ms
pp2048+tg256
8787
tokens/s
192
tokens/s
239
ms
pp2048+tg768
8728
tokens/s
185
tokens/s
240
ms
pp1024+tg1024
10185
tokens/s
193
tokens/s
112
ms
pp1280+tg3072
9763
tokens/s
184
tokens/s
137
ms
pp384+tg1152
11441
tokens/s
163
tokens/s
39
ms
pp64+tg1024
5947
tokens/s
165
tokens/s
16
ms
pp16+tg1536
532
tokens/s
183
tokens/s
36
ms