TEST #3553 RESULTS
05/16/2026 - 3:31 PM
ACCELERATOR
MODEL
182
tokens/s
generation
125
ms
time to first token
11598
tokens/s
prompt
2565
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
31.4GB
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
16190
tokens/s
157
tokens/s
70
ms
pp4096+tg256
8719
tokens/s
175
tokens/s
476
ms
pp2048+tg256
12370
tokens/s
183
tokens/s
172
ms
pp2048+tg768
12166
tokens/s
172
tokens/s
175
ms
pp1024+tg1024
14841
tokens/s
180
tokens/s
75
ms
pp1280+tg3072
13532
tokens/s
187
tokens/s
101
ms
pp384+tg1152
18575
tokens/s
199
tokens/s
28
ms
pp64+tg1024
6024
tokens/s
162
tokens/s
18
ms
pp16+tg1536
1970
tokens/s
226
tokens/s
13
ms