TEST #1998 RESULTS
12/21/2025 - 3:12 AM
ACCELERATOR
MODEL
108
tokens/s
generation
391
ms
time to first token
3709
tokens/s
prompt
1009
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 185H (alderlake)
RAM
23.4GB
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
4547
tokens/s
110
tokens/s
234
ms
pp4096+tg256
2785
tokens/s
94.1
tokens/s
1.48
sec
pp2048+tg256
3737
tokens/s
107
tokens/s
558
ms
pp2048+tg768
3733
tokens/s
106
tokens/s
558
ms
pp1024+tg1024
4472
tokens/s
112
tokens/s
238
ms
pp1280+tg3072
4192
tokens/s
103
tokens/s
315
ms
pp384+tg1152
5140
tokens/s
113
tokens/s
83
ms
pp64+tg1024
3918
tokens/s
115
tokens/s
25
ms
pp16+tg1536
853
tokens/s
114
tokens/s
27
ms