TEST #555 RESULTS
04/08/2025 - 4:59 AM
ACCELERATOR
MODEL
40.9
tokens/s
generation
2.18
sec
time to first token
601
tokens/s
prompt
224
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
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 21:12:54 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
721
tokens/s
46.0
tokens/s
1.44
sec
pp4096+tg256
527
tokens/s
27.3
tokens/s
7.81
sec
pp2048+tg256
657
tokens/s
37.2
tokens/s
3.14
sec
pp2048+tg768
656
tokens/s
35.5
tokens/s
3.15
sec
pp1024+tg1024
715
tokens/s
42.2
tokens/s
1.45
sec
pp1280+tg3072
707
tokens/s
33.5
tokens/s
1.83
sec
pp384+tg1152
721
tokens/s
46.9
tokens/s
551
ms
pp64+tg1024
512
tokens/s
51.0
tokens/s
144
ms
pp16+tg1536
191
tokens/s
48.5
tokens/s
100
ms