TEST #3572 RESULTS
05/19/2026 - 10:23 AM
ACCELERATOR
MODEL
124
tokens/s
generation
251
ms
time to first token
4930
tokens/s
prompt
1347
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11800H @ 2.30GHz (tigerlake)
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
7249
tokens/s
152
tokens/s
148
ms
pp4096+tg256
5091
tokens/s
131
tokens/s
812
ms
pp2048+tg256
6339
tokens/s
144
tokens/s
330
ms
pp2048+tg768
5993
tokens/s
111
tokens/s
350
ms
pp1024+tg1024
5138
tokens/s
116
tokens/s
208
ms
pp1280+tg3072
4874
tokens/s
106
tokens/s
271
ms
pp384+tg1152
5631
tokens/s
119
tokens/s
77
ms
pp64+tg1024
3406
tokens/s
122
tokens/s
27
ms
pp16+tg1536
651
tokens/s
118
tokens/s
33
ms