TEST #420 RESULTS
04/06/2025 - 8:10 PM
ACCELERATOR
MODEL
13.6
tokens/s
generation
8.92
sec
time to first token
137
tokens/s
prompt
59
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 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 20:24:23 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
176
tokens/s
16.6
tokens/s
5.89
sec
pp4096+tg256
152
tokens/s
13.2
tokens/s
27.01
sec
pp2048+tg256
150
tokens/s
15.2
tokens/s
13.69
sec
pp2048+tg768
144
tokens/s
14.2
tokens/s
14.32
sec
pp1024+tg1024
141
tokens/s
14.3
tokens/s
7.32
sec
pp1280+tg3072
152
tokens/s
12.3
tokens/s
8.51
sec
pp384+tg1152
151
tokens/s
12.3
tokens/s
2.60
sec
pp64+tg1024
114
tokens/s
11.9
tokens/s
627
ms
pp16+tg1536
56
tokens/s
12.3
tokens/s
355
ms