TEST #2281 RESULTS
01/14/2026 - 10:35 AM
ACCELERATOR
MODEL
65.6
tokens/s
generation
1.44
sec
time to first token
898
tokens/s
prompt
344
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
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:08:48 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1044
tokens/s
72.2
tokens/s
995
ms
pp4096+tg256
831
tokens/s
46.1
tokens/s
4.95
sec
pp2048+tg256
979
tokens/s
60.7
tokens/s
2.11
sec
pp2048+tg768
967
tokens/s
58.2
tokens/s
2.13
sec
pp1024+tg1024
1043
tokens/s
67.1
tokens/s
996
ms
pp1280+tg3072
1020
tokens/s
55.0
tokens/s
1.27
sec
pp384+tg1152
1014
tokens/s
74.3
tokens/s
391
ms
pp64+tg1024
852
tokens/s
79.9
tokens/s
87
ms
pp16+tg1536
328
tokens/s
76.6
tokens/s
60
ms