TEST #874 RESULTS
05/14/2025 - 10:57 PM
ACCELERATOR
MODEL
126
tokens/s
generation
268
ms
time to first token
5096
tokens/s
prompt
1339
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
15.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6569
tokens/s
131
tokens/s
166
ms
pp4096+tg256
4220
tokens/s
117
tokens/s
979
ms
pp2048+tg256
5506
tokens/s
133
tokens/s
379
ms
pp2048+tg768
5512
tokens/s
130
tokens/s
380
ms
pp1024+tg1024
6298
tokens/s
130
tokens/s
169
ms
pp1280+tg3072
5912
tokens/s
119
tokens/s
225
ms
pp384+tg1152
6967
tokens/s
126
tokens/s
62
ms
pp64+tg1024
3768
tokens/s
125
tokens/s
27
ms
pp16+tg1536
1110
tokens/s
123
tokens/s
21
ms