TEST #2408 RESULTS
01/31/2026 - 6:27 AM
ACCELERATOR
MODEL
639
tokens/s
generation
15
ms
time to first token
96076
tokens/s
prompt
16081
LocalScore
HOW YOU STACK UP
Explore All ResultsGranite 3.1 2b Instruct - Q6_K
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
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
138160
tokens/s
692
tokens/s
9
ms
pp4096+tg256
78372
tokens/s
597
tokens/s
54
ms
pp2048+tg256
117991
tokens/s
619
tokens/s
19
ms
pp2048+tg768
143049
tokens/s
636
tokens/s
16
ms
pp1024+tg1024
130179
tokens/s
644
tokens/s
9
ms
pp1280+tg3072
129877
tokens/s
617
tokens/s
12
ms
pp384+tg1152
102125
tokens/s
647
tokens/s
6
ms
pp64+tg1024
19159
tokens/s
665
tokens/s
5
ms
pp16+tg1536
5775
tokens/s
637
tokens/s
4
ms
