TEST #552 RESULTS
04/08/2025 - 2:32 AM
ACCELERATOR
MODEL
54.8
tokens/s
generation
1.81
sec
time to first token
652
tokens/s
prompt
270
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 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: 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
814
tokens/s
63.5
tokens/s
1.27
sec
pp4096+tg256
752
tokens/s
42.9
tokens/s
5.47
sec
pp2048+tg256
782
tokens/s
54.0
tokens/s
2.64
sec
pp2048+tg768
767
tokens/s
51.6
tokens/s
2.69
sec
pp1024+tg1024
690
tokens/s
57.0
tokens/s
1.50
sec
pp1280+tg3072
661
tokens/s
49.1
tokens/s
1.96
sec
pp384+tg1152
766
tokens/s
60.8
tokens/s
517
ms
pp64+tg1024
478
tokens/s
59.5
tokens/s
149
ms
pp16+tg1536
158
tokens/s
54.7
tokens/s
116
ms