TEST #2151 RESULTS
01/04/2026 - 9:24 AM
ACCELERATOR
MODEL
52.8
tokens/s
generation
1.81
sec
time to first token
717
tokens/s
prompt
275
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
840
tokens/s
60.4
tokens/s
1.24
sec
pp4096+tg256
652
tokens/s
33.7
tokens/s
6.31
sec
pp2048+tg256
776
tokens/s
47.0
tokens/s
2.66
sec
pp2048+tg768
778
tokens/s
44.8
tokens/s
2.65
sec
pp1024+tg1024
838
tokens/s
53.8
tokens/s
1.24
sec
pp1280+tg3072
826
tokens/s
41.9
tokens/s
1.57
sec
pp384+tg1152
838
tokens/s
61.6
tokens/s
472
ms
pp64+tg1024
665
tokens/s
68.1
tokens/s
109
ms
pp16+tg1536
238
tokens/s
64.3
tokens/s
80
ms