TEST #468 RESULTS
04/07/2025 - 4:07 AM
ACCELERATOR
MODEL
72.7
tokens/s
generation
1.13
sec
time to first token
1065
tokens/s
prompt
410
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
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 21:16:34 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1304
tokens/s
83.4
tokens/s
797
ms
pp4096+tg256
1122
tokens/s
47.8
tokens/s
3.67
sec
pp2048+tg256
1240
tokens/s
66.2
tokens/s
1.67
sec
pp2048+tg768
1247
tokens/s
62.8
tokens/s
1.66
sec
pp1024+tg1024
1295
tokens/s
73.8
tokens/s
803
ms
pp1280+tg3072
1274
tokens/s
59.0
tokens/s
1.02
sec
pp384+tg1152
1185
tokens/s
83.2
tokens/s
334
ms
pp64+tg1024
679
tokens/s
91.0
tokens/s
104
ms
pp16+tg1536
238
tokens/s
87.1
tokens/s
77
ms