TEST #1405 RESULTS
08/22/2025 - 2:14 AM
ACCELERATOR
MODEL
39.1
tokens/s
generation
2.21
sec
time to first token
596
tokens/s
prompt
219
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
23.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.3.0: Wed Dec 20 21:30:27 PST 2023; root:xnu-10002.81.5~7/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
715
tokens/s
45.3
tokens/s
1.45
sec
pp4096+tg256
518
tokens/s
26.6
tokens/s
7.94
sec
pp2048+tg256
651
tokens/s
36.3
tokens/s
3.17
sec
pp2048+tg768
651
tokens/s
34.7
tokens/s
3.17
sec
pp1024+tg1024
707
tokens/s
40.9
tokens/s
1.47
sec
pp1280+tg3072
691
tokens/s
31.7
tokens/s
1.88
sec
pp384+tg1152
716
tokens/s
43.5
tokens/s
555
ms
pp64+tg1024
521
tokens/s
47.6
tokens/s
140
ms
pp16+tg1536
192
tokens/s
45.0
tokens/s
101
ms