TEST #1341 RESULTS
08/08/2025 - 5:20 AM
ACCELERATOR
MODEL
55.6
tokens/s
generation
1.78
sec
time to first token
672
tokens/s
prompt
276
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
48GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
816
tokens/s
60.6
tokens/s
1.27
sec
pp4096+tg256
753
tokens/s
43.1
tokens/s
5.46
sec
pp2048+tg256
787
tokens/s
52.8
tokens/s
2.62
sec
pp2048+tg768
788
tokens/s
51.3
tokens/s
2.62
sec
pp1024+tg1024
765
tokens/s
56.7
tokens/s
1.36
sec
pp1280+tg3072
684
tokens/s
49.3
tokens/s
1.89
sec
pp384+tg1152
741
tokens/s
60.7
tokens/s
533
ms
pp64+tg1024
553
tokens/s
63.8
tokens/s
130
ms
pp16+tg1536
162
tokens/s
62.0
tokens/s
113
ms