TEST #3340 RESULTS
04/18/2026 - 12:13 AM
ACCELERATOR
MODEL
73.4
tokens/s
generation
1.30
sec
time to first token
1008
tokens/s
prompt
385
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
24GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:54:55 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1201
tokens/s
82.7
tokens/s
865
ms
pp4096+tg256
902
tokens/s
53.1
tokens/s
4.56
sec
pp2048+tg256
1090
tokens/s
68.4
tokens/s
1.89
sec
pp2048+tg768
1088
tokens/s
66.1
tokens/s
1.90
sec
pp1024+tg1024
1182
tokens/s
75.6
tokens/s
878
ms
pp1280+tg3072
1158
tokens/s
62.7
tokens/s
1.12
sec
pp384+tg1152
1186
tokens/s
83.3
tokens/s
335
ms
pp64+tg1024
922
tokens/s
87.7
tokens/s
80
ms
pp16+tg1536
340
tokens/s
81.4
tokens/s
57
ms