TEST #2072 RESULTS
01/01/2026 - 10:06 AM
ACCELERATOR
MODEL
57.7
tokens/s
generation
1.62
sec
time to first token
793
tokens/s
prompt
304
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:34:03 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
968
tokens/s
63.2
tokens/s
1.08
sec
pp4096+tg256
713
tokens/s
37.9
tokens/s
5.77
sec
pp2048+tg256
876
tokens/s
52.0
tokens/s
2.36
sec
pp2048+tg768
881
tokens/s
49.7
tokens/s
2.35
sec
pp1024+tg1024
968
tokens/s
58.8
tokens/s
1.08
sec
pp1280+tg3072
949
tokens/s
46.7
tokens/s
1.36
sec
pp384+tg1152
963
tokens/s
67.2
tokens/s
411
ms
pp64+tg1024
637
tokens/s
73.6
tokens/s
112
ms
pp16+tg1536
180
tokens/s
70.5
tokens/s
100
ms