TEST #202 RESULTS
04/03/2025 - 9:58 PM
ACCELERATOR
MODEL
14.7
tokens/s
generation
9.02
sec
time to first token
142
tokens/s
prompt
61
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:23:36 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
153
tokens/s
16.0
tokens/s
6.77
sec
pp4096+tg256
140
tokens/s
11.8
tokens/s
29.44
sec
pp2048+tg256
153
tokens/s
14.1
tokens/s
13.45
sec
pp2048+tg768
153
tokens/s
13.5
tokens/s
13.49
sec
pp1024+tg1024
159
tokens/s
14.8
tokens/s
6.50
sec
pp1280+tg3072
156
tokens/s
13.2
tokens/s
8.26
sec
pp384+tg1152
159
tokens/s
16.0
tokens/s
2.47
sec
pp64+tg1024
142
tokens/s
16.4
tokens/s
505
ms
pp16+tg1536
61
tokens/s
16.1
tokens/s
319
ms