TEST #380 RESULTS
04/06/2025 - 3:15 PM
ACCELERATOR
MODEL
111
tokens/s
generation
669
ms
time to first token
1846
tokens/s
prompt
674
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:17:35 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2202
tokens/s
125
tokens/s
473
ms
pp4096+tg256
1857
tokens/s
74.4
tokens/s
2.22
sec
pp2048+tg256
2097
tokens/s
101
tokens/s
987
ms
pp2048+tg768
2101
tokens/s
96.1
tokens/s
985
ms
pp1024+tg1024
2191
tokens/s
113
tokens/s
475
ms
pp1280+tg3072
2168
tokens/s
90.3
tokens/s
599
ms
pp384+tg1152
2125
tokens/s
127
tokens/s
187
ms
pp64+tg1024
1405
tokens/s
138
tokens/s
52
ms
pp16+tg1536
473
tokens/s
132
tokens/s
41
ms