TEST #1897 RESULTS
12/02/2025 - 9:19 PM
ACCELERATOR
MODEL
13.4
tokens/s
generation
11.51
sec
time to first token
109
tokens/s
prompt
50
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
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 19:32:47 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
129
tokens/s
15.1
tokens/s
8.03
sec
pp4096+tg256
116
tokens/s
10.6
tokens/s
35.46
sec
pp2048+tg256
121
tokens/s
13.2
tokens/s
16.97
sec
pp2048+tg768
118
tokens/s
12.3
tokens/s
17.50
sec
pp1024+tg1024
113
tokens/s
13.9
tokens/s
9.16
sec
pp1280+tg3072
107
tokens/s
11.4
tokens/s
12.06
sec
pp384+tg1152
115
tokens/s
14.4
tokens/s
3.42
sec
pp64+tg1024
114
tokens/s
15.2
tokens/s
621
ms
pp16+tg1536
47
tokens/s
14.4
tokens/s
402
ms