TEST #1469 RESULTS
09/03/2025 - 4:40 AM
ACCELERATOR
MODEL
105
tokens/s
generation
533
ms
time to first token
2458
tokens/s
prompt
786
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
64GB
OS
Darwin
Kernel Release
23.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.6.0: Thu Sep 12 23:36:23 PDT 2024; root:xnu-10063.141.1.701.1~1/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2827
tokens/s
113
tokens/s
373
ms
pp4096+tg256
2214
tokens/s
79.5
tokens/s
1.87
sec
pp2048+tg256
2729
tokens/s
100
tokens/s
763
ms
pp2048+tg768
2562
tokens/s
96.6
tokens/s
811
ms
pp1024+tg1024
3634
tokens/s
108
tokens/s
291
ms
pp1280+tg3072
2660
tokens/s
90.7
tokens/s
492
ms
pp384+tg1152
3502
tokens/s
116
tokens/s
115
ms
pp64+tg1024
1545
tokens/s
124
tokens/s
47
ms
pp16+tg1536
450
tokens/s
120
tokens/s
41
ms