TEST #2472 RESULTS
02/01/2026 - 10:37 AM
ACCELERATOR
MODEL
134
tokens/s
generation
165
ms
time to first token
9362
tokens/s
prompt
1967
LocalScore
HOW YOU STACK UP
Explore All ResultsLamoFast_2.0 - Q8_0
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
12643
tokens/s
120
tokens/s
90
ms
pp4096+tg256
6652
tokens/s
125
tokens/s
628
ms
pp2048+tg256
9622
tokens/s
132
tokens/s
221
ms
pp2048+tg768
9680
tokens/s
136
tokens/s
219
ms
pp1024+tg1024
12316
tokens/s
138
tokens/s
91
ms
pp1280+tg3072
11462
tokens/s
138
tokens/s
119
ms
pp384+tg1152
16038
tokens/s
143
tokens/s
31
ms
pp64+tg1024
4344
tokens/s
141
tokens/s
71
ms
pp16+tg1536
1502
tokens/s
139
tokens/s
19
ms