TEST #223 RESULTS
04/04/2025 - 4:02 AM
ACCELERATOR
MODEL
9.1
tokens/s
generation
15.23
sec
time to first token
80
tokens/s
prompt
36
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:06 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
97
tokens/s
10.6
tokens/s
10.66
sec
pp4096+tg256
87
tokens/s
7.8
tokens/s
47.14
sec
pp2048+tg256
96
tokens/s
9.5
tokens/s
21.53
sec
pp2048+tg768
90
tokens/s
9.0
tokens/s
22.90
sec
pp1024+tg1024
85
tokens/s
9.4
tokens/s
12.16
sec
pp1280+tg3072
82
tokens/s
7.7
tokens/s
15.70
sec
pp384+tg1152
71
tokens/s
8.8
tokens/s
5.53
sec
pp64+tg1024
78
tokens/s
9.8
tokens/s
917
ms
pp16+tg1536
34
tokens/s
9.3
tokens/s
558
ms