TEST #591 RESULTS
04/08/2025 - 11:49 AM
ACCELERATOR
MODEL
76.9
tokens/s
generation
1.18
sec
time to first token
1097
tokens/s
prompt
415
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:11:02 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1333
tokens/s
84.2
tokens/s
780
ms
pp4096+tg256
976
tokens/s
55.5
tokens/s
4.22
sec
pp2048+tg256
1204
tokens/s
71.3
tokens/s
1.71
sec
pp2048+tg768
1203
tokens/s
69.3
tokens/s
1.72
sec
pp1024+tg1024
1310
tokens/s
79.0
tokens/s
794
ms
pp1280+tg3072
1289
tokens/s
65.7
tokens/s
1.01
sec
pp384+tg1152
1363
tokens/s
86.7
tokens/s
292
ms
pp64+tg1024
874
tokens/s
92.8
tokens/s
83
ms
pp16+tg1536
321
tokens/s
87.9
tokens/s
60
ms