TEST #626 RESULTS
04/08/2025 - 11:24 PM
ACCELERATOR
MODEL
111
tokens/s
generation
683
ms
time to first token
1735
tokens/s
prompt
655
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
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
2192
tokens/s
124
tokens/s
475
ms
pp4096+tg256
1834
tokens/s
73.9
tokens/s
2.25
sec
pp2048+tg256
2060
tokens/s
99.9
tokens/s
1.00
sec
pp2048+tg768
2102
tokens/s
95.7
tokens/s
984
ms
pp1024+tg1024
2072
tokens/s
112
tokens/s
502
ms
pp1280+tg3072
2175
tokens/s
89.9
tokens/s
597
ms
pp384+tg1152
1842
tokens/s
127
tokens/s
215
ms
pp64+tg1024
1022
tokens/s
140
tokens/s
69
ms
pp16+tg1536
312
tokens/s
134
tokens/s
58
ms