TEST #219 RESULTS
04/04/2025 - 12:31 AM
ACCELERATOR
MODEL
136
tokens/s
generation
108
ms
time to first token
13164
tokens/s
prompt
2549
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 3700X 8-Core Processor (znver2)
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
16508
tokens/s
131
tokens/s
69
ms
pp4096+tg256
10529
tokens/s
134
tokens/s
396
ms
pp2048+tg256
15419
tokens/s
138
tokens/s
140
ms
pp2048+tg768
15256
tokens/s
122
tokens/s
142
ms
pp1024+tg1024
18909
tokens/s
130
tokens/s
63
ms
pp1280+tg3072
17538
tokens/s
144
tokens/s
79
ms
pp384+tg1152
18722
tokens/s
146
tokens/s
28
ms
pp64+tg1024
4922
tokens/s
130
tokens/s
23
ms
pp16+tg1536
673
tokens/s
146
tokens/s
31
ms