TEST #3428 RESULTS
05/03/2026 - 2:39 AM
ACCELERATOR
MODEL
111
tokens/s
generation
678
ms
time to first token
1782
tokens/s
prompt
663
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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:51:28 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2218
tokens/s
126
tokens/s
470
ms
pp4096+tg256
1840
tokens/s
73.9
tokens/s
2.24
sec
pp2048+tg256
2083
tokens/s
101
tokens/s
993
ms
pp2048+tg768
2019
tokens/s
95.5
tokens/s
1.02
sec
pp1024+tg1024
2183
tokens/s
113
tokens/s
477
ms
pp1280+tg3072
2194
tokens/s
90.5
tokens/s
592
ms
pp384+tg1152
2002
tokens/s
127
tokens/s
199
ms
pp64+tg1024
1122
tokens/s
139
tokens/s
64
ms
pp16+tg1536
377
tokens/s
132
tokens/s
49
ms