TEST #1004 RESULTS
06/06/2025 - 5:05 AM
ACCELERATOR
MODEL
121
tokens/s
generation
490
ms
time to first token
2512
tokens/s
prompt
852
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X3D 8-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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3548
tokens/s
136
tokens/s
296
ms
pp4096+tg256
2448
tokens/s
86.2
tokens/s
1.69
sec
pp2048+tg256
2950
tokens/s
98.1
tokens/s
705
ms
pp2048+tg768
2940
tokens/s
92.8
tokens/s
707
ms
pp1024+tg1024
3151
tokens/s
119
tokens/s
333
ms
pp1280+tg3072
3123
tokens/s
87.9
tokens/s
418
ms
pp384+tg1152
2633
tokens/s
144
tokens/s
152
ms
pp64+tg1024
766
tokens/s
168
tokens/s
90
ms
pp16+tg1536
1050
tokens/s
154
tokens/s
22
ms