TEST #1312 RESULTS
08/05/2025 - 11:32 AM
ACCELERATOR
MODEL
77.7
tokens/s
generation
1.18
sec
time to first token
1104
tokens/s
prompt
418
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
1341
tokens/s
86.0
tokens/s
776
ms
pp4096+tg256
983
tokens/s
55.9
tokens/s
4.18
sec
pp2048+tg256
1217
tokens/s
72.0
tokens/s
1.70
sec
pp2048+tg768
1208
tokens/s
69.9
tokens/s
1.71
sec
pp1024+tg1024
1320
tokens/s
79.0
tokens/s
787
ms
pp1280+tg3072
1300
tokens/s
65.8
tokens/s
996
ms
pp384+tg1152
1328
tokens/s
87.1
tokens/s
300
ms
pp64+tg1024
927
tokens/s
93.6
tokens/s
79
ms
pp16+tg1536
307
tokens/s
90.0
tokens/s
62
ms