TEST #3418 RESULTS
04/29/2026 - 3:45 PM
ACCELERATOR
MODEL
101
tokens/s
generation
422
ms
time to first token
3337
tokens/s
prompt
928
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-7700T CPU @ 2.90GHz (skylake)
RAM
47.4GB
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
4132
tokens/s
104
tokens/s
258
ms
pp4096+tg256
2610
tokens/s
81.6
tokens/s
1.58
sec
pp2048+tg256
3441
tokens/s
101
tokens/s
605
ms
pp2048+tg768
3474
tokens/s
98.3
tokens/s
600
ms
pp1024+tg1024
4155
tokens/s
103
tokens/s
255
ms
pp1280+tg3072
3865
tokens/s
96.6
tokens/s
343
ms
pp384+tg1152
4923
tokens/s
110
tokens/s
87
ms
pp64+tg1024
2831
tokens/s
105
tokens/s
33
ms
pp16+tg1536
605
tokens/s
111
tokens/s
35
ms