TEST #2988 RESULTS
03/06/2026 - 8:27 AM
ACCELERATOR
MODEL
9.7
tokens/s
generation
14.42
sec
time to first token
88
tokens/s
prompt
39
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jan 19 21:58:37 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
99
tokens/s
10.7
tokens/s
10.43
sec
pp4096+tg256
89
tokens/s
7.9
tokens/s
46.27
sec
pp2048+tg256
96
tokens/s
9.5
tokens/s
21.44
sec
pp2048+tg768
95
tokens/s
9.3
tokens/s
21.58
sec
pp1024+tg1024
98
tokens/s
10.1
tokens/s
10.52
sec
pp1280+tg3072
93
tokens/s
8.7
tokens/s
13.85
sec
pp384+tg1152
90
tokens/s
10.2
tokens/s
4.38
sec
pp64+tg1024
91
tokens/s
10.6
tokens/s
792
ms
pp16+tg1536
41
tokens/s
10.2
tokens/s
478
ms