TEST #3644 RESULTS
05/29/2026 - 5:31 AM
ACCELERATOR
MODEL
7.0
tokens/s
generation
59.45
sec
time to first token
23
tokens/s
prompt
14
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i5-11400H @ 2.70GHz (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
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
24
tokens/s
7.5
tokens/s
43.50
sec
pp4096+tg256
21
tokens/s
5.9
tokens/s
193.94
sec
pp2048+tg256
23
tokens/s
6.9
tokens/s
89.17
sec
pp2048+tg768
23
tokens/s
6.7
tokens/s
90.07
sec
pp1024+tg1024
24
tokens/s
7.1
tokens/s
43.16
sec
pp1280+tg3072
23
tokens/s
6.6
tokens/s
55.03
sec
pp384+tg1152
23
tokens/s
7.5
tokens/s
16.55
sec
pp64+tg1024
24
tokens/s
7.6
tokens/s
2.84
sec
pp16+tg1536
25
tokens/s
7.4
tokens/s
762
ms