TEST #1203 RESULTS
07/09/2025 - 11:07 AM
ACCELERATOR
MODEL
2.2
tokens/s
generation
186.15
sec
time to first token
6
tokens/s
prompt
4
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-1335U (alderlake)
RAM
63.2GB
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
7
tokens/s
2.0
tokens/s
149.92
sec
pp4096+tg256
7
tokens/s
1.8
tokens/s
557.90
sec
pp2048+tg256
8
tokens/s
2.1
tokens/s
255.50
sec
pp2048+tg768
7
tokens/s
2.1
tokens/s
291.29
sec
pp1024+tg1024
6
tokens/s
2.3
tokens/s
162.03
sec
pp1280+tg3072
7
tokens/s
2.0
tokens/s
189.00
sec
pp384+tg1152
8
tokens/s
2.4
tokens/s
48.62
sec
pp64+tg1024
4
tokens/s
2.4
tokens/s
15.83
sec
pp16+tg1536
3
tokens/s
2.4
tokens/s
5.25
sec