TEST #3107 RESULTS
03/18/2026 - 6:37 AM
ACCELERATOR
MODEL
61.6
tokens/s
generation
1.91
sec
time to first token
630
tokens/s
prompt
273
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M5 Max 6P+12E
RAM
36GB
OS
Darwin
Kernel Release
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:54:38 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6050
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
745
tokens/s
66.3
tokens/s
1.39
sec
pp4096+tg256
682
tokens/s
52.2
tokens/s
6.02
sec
pp2048+tg256
714
tokens/s
59.9
tokens/s
2.89
sec
pp2048+tg768
715
tokens/s
58.5
tokens/s
2.88
sec
pp1024+tg1024
732
tokens/s
62.6
tokens/s
1.42
sec
pp1280+tg3072
705
tokens/s
57.7
tokens/s
1.83
sec
pp384+tg1152
710
tokens/s
66.6
tokens/s
555
ms
pp64+tg1024
484
tokens/s
67.1
tokens/s
146
ms
pp16+tg1536
185
tokens/s
63.8
tokens/s
100
ms