TEST #414 RESULTS
04/06/2025 - 7:40 PM
ACCELERATOR
MODEL
67.9
tokens/s
generation
1.41
sec
time to first token
939
tokens/s
prompt
356
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
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
1124
tokens/s
76.3
tokens/s
924
ms
pp4096+tg256
815
tokens/s
46.9
tokens/s
5.05
sec
pp2048+tg256
1005
tokens/s
62.2
tokens/s
2.05
sec
pp2048+tg768
1008
tokens/s
59.3
tokens/s
2.05
sec
pp1024+tg1024
1121
tokens/s
69.5
tokens/s
926
ms
pp1280+tg3072
1100
tokens/s
57.1
tokens/s
1.18
sec
pp384+tg1152
1137
tokens/s
77.1
tokens/s
349
ms
pp64+tg1024
843
tokens/s
83.1
tokens/s
87
ms
pp16+tg1536
296
tokens/s
79.6
tokens/s
65
ms