TEST #2710 RESULTS
02/17/2026 - 11:50 PM
ACCELERATOR
MODEL
865
tokens/s
generation
50
ms
time to first token
39062
tokens/s
prompt
8799
LocalScore
HOW YOU STACK UP
Explore All ResultsTinyStories 656K - Q3_K - Large
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
54544
tokens/s
785
tokens/s
20
ms
pp4096+tg256
47379
tokens/s
814
tokens/s
88
ms
pp2048+tg256
36447
tokens/s
901
tokens/s
58
ms
pp2048+tg768
21693
tokens/s
950
tokens/s
96
ms
pp1024+tg1024
41070
tokens/s
933
tokens/s
33
ms
pp1280+tg3072
114954
tokens/s
910
tokens/s
12
ms
pp384+tg1152
29006
tokens/s
973
tokens/s
16
ms
pp64+tg1024
600
tokens/s
789
tokens/s
119
ms
pp16+tg1536
5868
tokens/s
734
tokens/s
4
ms