TEST #1395 RESULTS
08/18/2025 - 11:05 PM
ACCELERATOR
MODEL
65.8
tokens/s
generation
1.44
sec
time to first token
903
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/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
73.8
tokens/s
993
ms
pp4096+tg256
833
tokens/s
46.3
tokens/s
4.94
sec
pp2048+tg256
975
tokens/s
60.9
tokens/s
2.12
sec
pp2048+tg768
972
tokens/s
58.0
tokens/s
2.12
sec
pp1024+tg1024
1041
tokens/s
66.4
tokens/s
998
ms
pp1280+tg3072
1022
tokens/s
54.7
tokens/s
1.27
sec
pp384+tg1152
1055
tokens/s
74.5
tokens/s
376
ms
pp64+tg1024
855
tokens/s
80.2
tokens/s
86
ms
pp16+tg1536
327
tokens/s
77.1
tokens/s
61
ms