TEST #865 RESULTS
05/14/2025 - 8:32 AM
ACCELERATOR
MODEL
135
tokens/s
generation
280
ms
time to first token
4908
tokens/s
prompt
1332
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
6352
tokens/s
141
tokens/s
168
ms
pp4096+tg256
4055
tokens/s
116
tokens/s
1.02
sec
pp2048+tg256
5280
tokens/s
131
tokens/s
395
ms
pp2048+tg768
5213
tokens/s
130
tokens/s
400
ms
pp1024+tg1024
6110
tokens/s
134
tokens/s
179
ms
pp1280+tg3072
5740
tokens/s
123
tokens/s
230
ms
pp384+tg1152
8004
tokens/s
147
tokens/s
55
ms
pp64+tg1024
3015
tokens/s
139
tokens/s
28
ms
pp16+tg1536
403
tokens/s
152
tokens/s
46
ms