TEST #1550 RESULTS
09/24/2025 - 7:25 AM
ACCELERATOR
MODEL
74.4
tokens/s
generation
1.30
sec
time to first token
982
tokens/s
prompt
383
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
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:12:01 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1204
tokens/s
82.6
tokens/s
862
ms
pp4096+tg256
908
tokens/s
53.1
tokens/s
4.53
sec
pp2048+tg256
1081
tokens/s
68.9
tokens/s
1.91
sec
pp2048+tg768
1093
tokens/s
66.2
tokens/s
1.89
sec
pp1024+tg1024
1151
tokens/s
75.9
tokens/s
902
ms
pp1280+tg3072
1160
tokens/s
62.9
tokens/s
1.12
sec
pp384+tg1152
1100
tokens/s
83.8
tokens/s
360
ms
pp64+tg1024
922
tokens/s
89.6
tokens/s
80
ms
pp16+tg1536
221
tokens/s
86.2
tokens/s
83
ms