TEST #750 RESULTS
04/21/2025 - 2:32 PM
ACCELERATOR
MODEL
45.6
tokens/s
generation
2.03
sec
time to first token
591
tokens/s
prompt
237
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
128GB
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
701
tokens/s
49.7
tokens/s
1.48
sec
pp4096+tg256
643
tokens/s
34.8
tokens/s
6.39
sec
pp2048+tg256
673
tokens/s
42.2
tokens/s
3.06
sec
pp2048+tg768
680
tokens/s
41.8
tokens/s
3.03
sec
pp1024+tg1024
687
tokens/s
46.5
tokens/s
1.51
sec
pp1280+tg3072
677
tokens/s
40.2
tokens/s
1.91
sec
pp384+tg1152
673
tokens/s
50.8
tokens/s
589
ms
pp64+tg1024
441
tokens/s
53.0
tokens/s
162
ms
pp16+tg1536
146
tokens/s
51.0
tokens/s
127
ms