TEST #3430 RESULTS
05/03/2026 - 11:34 AM
ACCELERATOR
MODEL
66.3
tokens/s
generation
1.44
sec
time to first token
902
tokens/s
prompt
346
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
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:31:09 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1045
tokens/s
73.9
tokens/s
994
ms
pp4096+tg256
835
tokens/s
46.6
tokens/s
4.92
sec
pp2048+tg256
973
tokens/s
61.0
tokens/s
2.12
sec
pp2048+tg768
975
tokens/s
58.7
tokens/s
2.12
sec
pp1024+tg1024
1042
tokens/s
67.7
tokens/s
997
ms
pp1280+tg3072
1029
tokens/s
55.6
tokens/s
1.26
sec
pp384+tg1152
1048
tokens/s
75.0
tokens/s
379
ms
pp64+tg1024
854
tokens/s
80.3
tokens/s
86
ms
pp16+tg1536
319
tokens/s
77.5
tokens/s
62
ms