TEST #164 RESULTS
03/30/2025 - 7:54 PM
ACCELERATOR
MODEL
47.2
tokens/s
generation
2.20
sec
time to first token
551
tokens/s
prompt
228
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Nov 14 18:15:21 PST 2024; root:xnu-11215.41.3~13/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
664
tokens/s
52.6
tokens/s
1.56
sec
pp4096+tg256
597
tokens/s
38.3
tokens/s
6.89
sec
pp2048+tg256
644
tokens/s
46.7
tokens/s
3.20
sec
pp2048+tg768
642
tokens/s
45.5
tokens/s
3.21
sec
pp1024+tg1024
595
tokens/s
49.9
tokens/s
1.74
sec
pp1280+tg3072
563
tokens/s
43.6
tokens/s
2.29
sec
pp384+tg1152
610
tokens/s
48.9
tokens/s
648
ms
pp64+tg1024
478
tokens/s
50.1
tokens/s
152
ms
pp16+tg1536
164
tokens/s
49.0
tokens/s
115
ms