TEST #732 RESULTS
04/17/2025 - 8:38 AM
ACCELERATOR
MODEL
27.5
tokens/s
generation
1.70
sec
time to first token
789
tokens/s
prompt
234
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700H (alderlake)
RAM
31.6GB
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
872
tokens/s
27.5
tokens/s
1.21
sec
pp4096+tg256
712
tokens/s
25.1
tokens/s
5.79
sec
pp2048+tg256
836
tokens/s
27.4
tokens/s
2.49
sec
pp2048+tg768
836
tokens/s
27.1
tokens/s
2.49
sec
pp1024+tg1024
913
tokens/s
28.0
tokens/s
1.16
sec
pp1280+tg3072
867
tokens/s
26.5
tokens/s
1.51
sec
pp384+tg1152
952
tokens/s
28.3
tokens/s
438
ms
pp64+tg1024
815
tokens/s
28.9
tokens/s
113
ms
pp16+tg1536
303
tokens/s
28.5
tokens/s
86
ms