TEST #789 RESULTS
05/01/2025 - 6:30 AM
ACCELERATOR
MODEL
133
tokens/s
generation
476
ms
time to first token
2520
tokens/s
prompt
889
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 10P+4E
RAM
96GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:40 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3144
tokens/s
148
tokens/s
332
ms
pp4096+tg256
2630
tokens/s
92.5
tokens/s
1.57
sec
pp2048+tg256
3001
tokens/s
123
tokens/s
691
ms
pp2048+tg768
3027
tokens/s
117
tokens/s
685
ms
pp1024+tg1024
3056
tokens/s
136
tokens/s
342
ms
pp1280+tg3072
3037
tokens/s
111
tokens/s
429
ms
pp384+tg1152
2921
tokens/s
150
tokens/s
138
ms
pp64+tg1024
1494
tokens/s
162
tokens/s
48
ms
pp16+tg1536
371
tokens/s
155
tokens/s
49
ms