TEST #1138 RESULTS
06/27/2025 - 12:45 PM
ACCELERATOR
MODEL
65.8
tokens/s
generation
1.43
sec
time to first token
906
tokens/s
prompt
346
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
23.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.5.0: Wed May 1 20:14:59 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1111
tokens/s
74.1
tokens/s
935
ms
pp4096+tg256
808
tokens/s
46.4
tokens/s
5.09
sec
pp2048+tg256
992
tokens/s
61.2
tokens/s
2.08
sec
pp2048+tg768
991
tokens/s
58.8
tokens/s
2.08
sec
pp1024+tg1024
1099
tokens/s
66.3
tokens/s
946
ms
pp1280+tg3072
1057
tokens/s
55.3
tokens/s
1.23
sec
pp384+tg1152
1074
tokens/s
74.9
tokens/s
370
ms
pp64+tg1024
772
tokens/s
77.8
tokens/s
94
ms
pp16+tg1536
252
tokens/s
77.1
tokens/s
74
ms