TEST #1192 RESULTS
07/07/2025 - 6:02 PM
ACCELERATOR
MODEL
168
tokens/s
generation
284
ms
time to first token
4875
tokens/s
prompt
1422
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
QEMU Virtual CPU version 2.5+
RAM
11.7GB
OS
Linux
Kernel Release
6.8.0-63-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #66-Ubuntu SMP PREEMPT_DYNAMIC Fri Jun 13 20:25:30 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6034
tokens/s
186
tokens/s
175
ms
pp4096+tg256
4095
tokens/s
119
tokens/s
1.01
sec
pp2048+tg256
5221
tokens/s
155
tokens/s
399
ms
pp2048+tg768
5213
tokens/s
150
tokens/s
399
ms
pp1024+tg1024
5995
tokens/s
172
tokens/s
176
ms
pp1280+tg3072
5702
tokens/s
142
tokens/s
230
ms
pp384+tg1152
6670
tokens/s
188
tokens/s
62
ms
pp64+tg1024
4758
tokens/s
202
tokens/s
18
ms
pp16+tg1536
185
tokens/s
194
tokens/s
91
ms