TEST #2153 RESULTS
01/04/2026 - 10:26 AM
ACCELERATOR
MODEL
12.9
tokens/s
generation
10.95
sec
time to first token
114
tokens/s
prompt
51
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:34:03 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
129
tokens/s
15.3
tokens/s
7.97
sec
pp4096+tg256
116
tokens/s
10.9
tokens/s
35.25
sec
pp2048+tg256
125
tokens/s
13.3
tokens/s
16.40
sec
pp2048+tg768
125
tokens/s
13.0
tokens/s
16.40
sec
pp1024+tg1024
129
tokens/s
14.4
tokens/s
7.98
sec
pp1280+tg3072
128
tokens/s
10.7
tokens/s
10.04
sec
pp384+tg1152
115
tokens/s
12.7
tokens/s
3.41
sec
pp64+tg1024
107
tokens/s
13.3
tokens/s
665
ms
pp16+tg1536
50
tokens/s
12.8
tokens/s
386
ms