TEST #1781 RESULTS
11/12/2025 - 5:48 AM
ACCELERATOR
MODEL
23.8
tokens/s
generation
2.74
sec
time to first token
521
tokens/s
prompt
165
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i3-12100F (alderlake)
RAM
7.8GB
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
578
tokens/s
29.6
tokens/s
1.80
sec
pp4096+tg256
423
tokens/s
9.1
tokens/s
9.79
sec
pp2048+tg256
513
tokens/s
16.5
tokens/s
4.05
sec
pp2048+tg768
511
tokens/s
14.9
tokens/s
4.07
sec
pp1024+tg1024
571
tokens/s
21.9
tokens/s
1.83
sec
pp1280+tg3072
555
tokens/s
13.1
tokens/s
2.35
sec
pp384+tg1152
622
tokens/s
30.9
tokens/s
637
ms
pp64+tg1024
614
tokens/s
43.1
tokens/s
116
ms
pp16+tg1536
298
tokens/s
35.1
tokens/s
63
ms