TEST #1791 RESULTS
11/13/2025 - 6:33 AM
ACCELERATOR
MODEL
17.7
tokens/s
generation
6.85
sec
time to first token
186
tokens/s
prompt
78
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
32GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
209
tokens/s
18.7
tokens/s
4.96
sec
pp4096+tg256
184
tokens/s
15.2
tokens/s
22.30
sec
pp2048+tg256
201
tokens/s
17.3
tokens/s
10.25
sec
pp2048+tg768
201
tokens/s
17.0
tokens/s
10.25
sec
pp1024+tg1024
208
tokens/s
18.1
tokens/s
4.97
sec
pp1280+tg3072
203
tokens/s
16.5
tokens/s
6.35
sec
pp384+tg1152
202
tokens/s
18.7
tokens/s
1.95
sec
pp64+tg1024
185
tokens/s
19.2
tokens/s
396
ms
pp16+tg1536
84
tokens/s
18.9
tokens/s
242
ms