TEST #3375 RESULTS
04/24/2026 - 11:57 AM
ACCELERATOR
MODEL
153
tokens/s
generation
357
ms
time to first token
3348
tokens/s
prompt
1128
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:26:07 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4258
tokens/s
175
tokens/s
246
ms
pp4096+tg256
3465
tokens/s
103
tokens/s
1.19
sec
pp2048+tg256
4086
tokens/s
139
tokens/s
509
ms
pp2048+tg768
4123
tokens/s
132
tokens/s
504
ms
pp1024+tg1024
4251
tokens/s
154
tokens/s
247
ms
pp1280+tg3072
3997
tokens/s
124
tokens/s
326
ms
pp384+tg1152
3680
tokens/s
174
tokens/s
114
ms
pp64+tg1024
1785
tokens/s
194
tokens/s
41
ms
pp16+tg1536
489
tokens/s
183
tokens/s
38
ms