TEST #1659 RESULTS
10/16/2025 - 4:22 PM
ACCELERATOR
MODEL
38.3
tokens/s
generation
2.43
sec
time to first token
535
tokens/s
prompt
203
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
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 11:30:34 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
637
tokens/s
43.0
tokens/s
1.63
sec
pp4096+tg256
480
tokens/s
24.9
tokens/s
8.57
sec
pp2048+tg256
587
tokens/s
34.5
tokens/s
3.51
sec
pp2048+tg768
587
tokens/s
33.0
tokens/s
3.52
sec
pp1024+tg1024
630
tokens/s
38.9
tokens/s
1.65
sec
pp1280+tg3072
616
tokens/s
30.8
tokens/s
2.10
sec
pp384+tg1152
638
tokens/s
44.4
tokens/s
622
ms
pp64+tg1024
461
tokens/s
48.7
tokens/s
156
ms
pp16+tg1536
173
tokens/s
46.2
tokens/s
110
ms