TEST #499 RESULTS
04/07/2025 - 3:31 PM
ACCELERATOR
MODEL
14.9
tokens/s
generation
8.96
sec
time to first token
143
tokens/s
prompt
62
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 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 20:23:36 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
160
tokens/s
16.5
tokens/s
6.47
sec
pp4096+tg256
141
tokens/s
11.7
tokens/s
29.16
sec
pp2048+tg256
153
tokens/s
14.2
tokens/s
13.49
sec
pp2048+tg768
153
tokens/s
13.7
tokens/s
13.45
sec
pp1024+tg1024
156
tokens/s
15.0
tokens/s
6.63
sec
pp1280+tg3072
157
tokens/s
13.3
tokens/s
8.22
sec
pp384+tg1152
161
tokens/s
16.2
tokens/s
2.44
sec
pp64+tg1024
147
tokens/s
16.9
tokens/s
489
ms
pp16+tg1536
60
tokens/s
16.2
tokens/s
319
ms