TEST #3260 RESULTS
04/09/2026 - 1:47 PM
ACCELERATOR
MODEL
8.9
tokens/s
generation
14.35
sec
time to first token
84
tokens/s
prompt
37
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: Fri Feb 27 19:34:43 PST 2026; root:xnu-11417.140.69.709.8~1/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
107
tokens/s
10.5
tokens/s
9.66
sec
pp4096+tg256
94
tokens/s
7.9
tokens/s
43.84
sec
pp2048+tg256
98
tokens/s
9.0
tokens/s
20.93
sec
pp2048+tg768
92
tokens/s
8.8
tokens/s
22.49
sec
pp1024+tg1024
91
tokens/s
9.4
tokens/s
11.33
sec
pp1280+tg3072
89
tokens/s
8.0
tokens/s
14.49
sec
pp384+tg1152
80
tokens/s
9.0
tokens/s
4.87
sec
pp64+tg1024
75
tokens/s
8.8
tokens/s
951
ms
pp16+tg1536
30
tokens/s
8.6
tokens/s
635
ms