TEST #422 RESULTS
04/06/2025 - 8:20 PM
ACCELERATOR
MODEL
20.0
tokens/s
generation
7.23
sec
time to first token
173
tokens/s
prompt
78
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:16:34 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
188
tokens/s
21.1
tokens/s
5.49
sec
pp4096+tg256
180
tokens/s
15.3
tokens/s
22.77
sec
pp2048+tg256
196
tokens/s
18.9
tokens/s
10.49
sec
pp2048+tg768
177
tokens/s
18.6
tokens/s
11.64
sec
pp1024+tg1024
200
tokens/s
20.5
tokens/s
5.16
sec
pp1280+tg3072
189
tokens/s
18.0
tokens/s
6.81
sec
pp384+tg1152
197
tokens/s
22.2
tokens/s
2.00
sec
pp64+tg1024
164
tokens/s
22.7
tokens/s
434
ms
pp16+tg1536
66
tokens/s
22.5
tokens/s
285
ms