TEST #1901 RESULTS
12/03/2025 - 10:02 AM
ACCELERATOR
MODEL
99.0
tokens/s
generation
2.92
sec
time to first token
484
tokens/s
prompt
254
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 285K (arrowlake-s)
RAM
47.3GB
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
505
tokens/s
103
tokens/s
2.04
sec
pp4096+tg256
410
tokens/s
86.1
tokens/s
10.01
sec
pp2048+tg256
471
tokens/s
97.3
tokens/s
4.36
sec
pp2048+tg768
470
tokens/s
94.8
tokens/s
4.37
sec
pp1024+tg1024
505
tokens/s
100
tokens/s
2.04
sec
pp1280+tg3072
501
tokens/s
92.4
tokens/s
2.57
sec
pp384+tg1152
529
tokens/s
105
tokens/s
735
ms
pp64+tg1024
501
tokens/s
107
tokens/s
138
ms
pp16+tg1536
468
tokens/s
106
tokens/s
44
ms