TEST #3547 RESULTS
05/16/2026 - 8:19 AM
ACCELERATOR
MODEL
226
tokens/s
generation
118
ms
time to first token
11437
tokens/s
prompt
2800
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i7-13700KF (alderlake)
RAM
63.8GB
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
14594
tokens/s
187
tokens/s
76
ms
pp4096+tg256
9924
tokens/s
209
tokens/s
417
ms
pp2048+tg256
12229
tokens/s
234
tokens/s
172
ms
pp2048+tg768
12720
tokens/s
230
tokens/s
165
ms
pp1024+tg1024
15025
tokens/s
233
tokens/s
73
ms
pp1280+tg3072
14019
tokens/s
228
tokens/s
95
ms
pp384+tg1152
15376
tokens/s
238
tokens/s
29
ms
pp64+tg1024
7996
tokens/s
239
tokens/s
12
ms
pp16+tg1536
1048
tokens/s
240
tokens/s
21
ms