TEST #2555 RESULTS
02/07/2026 - 4:52 AM
ACCELERATOR
MODEL
123
tokens/s
generation
586
ms
time to first token
1935
tokens/s
prompt
740
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Max 8P+4E
RAM
32GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Wed Nov 5 21:32:34 PST 2025; root:xnu-11417.140.69.705.2~1/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2696
tokens/s
156
tokens/s
386
ms
pp4096+tg256
2475
tokens/s
95.7
tokens/s
1.67
sec
pp2048+tg256
2693
tokens/s
124
tokens/s
769
ms
pp2048+tg768
2106
tokens/s
109
tokens/s
982
ms
pp1024+tg1024
2168
tokens/s
120
tokens/s
481
ms
pp1280+tg3072
1963
tokens/s
99.8
tokens/s
661
ms
pp384+tg1152
2093
tokens/s
129
tokens/s
190
ms
pp64+tg1024
968
tokens/s
139
tokens/s
71
ms
pp16+tg1536
256
tokens/s
131
tokens/s
68
ms