TEST #3415 RESULTS
04/29/2026 - 11:32 AM
ACCELERATOR
MODEL
108
tokens/s
generation
422
ms
time to first token
3407
tokens/s
prompt
955
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
4153
tokens/s
118
tokens/s
255
ms
pp4096+tg256
2606
tokens/s
92.4
tokens/s
1.58
sec
pp2048+tg256
3463
tokens/s
105
tokens/s
612
ms
pp2048+tg768
3446
tokens/s
103
tokens/s
605
ms
pp1024+tg1024
4141
tokens/s
109
tokens/s
257
ms
pp1280+tg3072
3872
tokens/s
100
tokens/s
340
ms
pp384+tg1152
4905
tokens/s
113
tokens/s
87
ms
pp64+tg1024
3393
tokens/s
116
tokens/s
27
ms
pp16+tg1536
686
tokens/s
115
tokens/s
32
ms