TEST #3463 RESULTS
05/07/2026 - 5:29 PM
ACCELERATOR
MODEL
209
tokens/s
generation
122
ms
time to first token
11348
tokens/s
prompt
2687
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
31.9GB
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
14318
tokens/s
206
tokens/s
77
ms
pp4096+tg256
10238
tokens/s
201
tokens/s
406
ms
pp2048+tg256
13192
tokens/s
212
tokens/s
161
ms
pp2048+tg768
13130
tokens/s
213
tokens/s
161
ms
pp1024+tg1024
14857
tokens/s
217
tokens/s
74
ms
pp1280+tg3072
14345
tokens/s
200
tokens/s
94
ms
pp384+tg1152
15795
tokens/s
208
tokens/s
29
ms
pp64+tg1024
6045
tokens/s
208
tokens/s
17
ms
pp16+tg1536
213
tokens/s
213
tokens/s
80
ms