TEST #3341 RESULTS
04/18/2026 - 12:30 AM
ACCELERATOR
MODEL
13.0
tokens/s
generation
9.78
sec
time to first token
120
tokens/s
prompt
54
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
24GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:54:55 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
180
tokens/s
18.6
tokens/s
5.75
sec
pp4096+tg256
155
tokens/s
14.6
tokens/s
26.49
sec
pp2048+tg256
159
tokens/s
15.1
tokens/s
12.92
sec
pp2048+tg768
122
tokens/s
9.7
tokens/s
16.83
sec
pp1024+tg1024
111
tokens/s
11.5
tokens/s
9.33
sec
pp1280+tg3072
108
tokens/s
9.6
tokens/s
11.90
sec
pp384+tg1152
108
tokens/s
12.6
tokens/s
3.62
sec
pp64+tg1024
95
tokens/s
13.0
tokens/s
766
ms
pp16+tg1536
43
tokens/s
12.0
tokens/s
450
ms