TEST #1282 RESULTS
08/01/2025 - 9:08 AM
ACCELERATOR
MODEL
38.9
tokens/s
generation
2.43
sec
time to first token
537
tokens/s
prompt
205
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
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:48:46 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
643
tokens/s
44.2
tokens/s
1.61
sec
pp4096+tg256
470
tokens/s
25.4
tokens/s
8.75
sec
pp2048+tg256
595
tokens/s
35.1
tokens/s
3.47
sec
pp2048+tg768
596
tokens/s
33.4
tokens/s
3.46
sec
pp1024+tg1024
636
tokens/s
40.0
tokens/s
1.63
sec
pp1280+tg3072
626
tokens/s
31.4
tokens/s
2.07
sec
pp384+tg1152
638
tokens/s
45.4
tokens/s
622
ms
pp64+tg1024
444
tokens/s
49.8
tokens/s
162
ms
pp16+tg1536
182
tokens/s
45.3
tokens/s
105
ms