TEST #2164 RESULTS
01/07/2026 - 8:53 AM
ACCELERATOR
MODEL
111
tokens/s
generation
680
ms
time to first token
1774
tokens/s
prompt
662
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2183
tokens/s
127
tokens/s
477
ms
pp4096+tg256
1833
tokens/s
73.9
tokens/s
2.25
sec
pp2048+tg256
2091
tokens/s
101
tokens/s
989
ms
pp2048+tg768
2068
tokens/s
96.0
tokens/s
1.00
sec
pp1024+tg1024
2138
tokens/s
113
tokens/s
487
ms
pp1280+tg3072
2127
tokens/s
90.2
tokens/s
610
ms
pp384+tg1152
2123
tokens/s
128
tokens/s
188
ms
pp64+tg1024
1068
tokens/s
140
tokens/s
66
ms
pp16+tg1536
339
tokens/s
132
tokens/s
54
ms