TEST #688 RESULTS
04/11/2025 - 5:10 AM
ACCELERATOR
MODEL
7.2
tokens/s
generation
16.27
sec
time to first token
75
tokens/s
prompt
32
LocalScore
HOW YOU STACK UP
Explore All ResultsMistral Small 3.1 24B Instruct 2503 - Q6_K
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
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
88
tokens/s
8.3
tokens/s
11.74
sec
pp4096+tg256
82
tokens/s
6.9
tokens/s
49.85
sec
pp2048+tg256
83
tokens/s
7.2
tokens/s
24.90
sec
pp2048+tg768
82
tokens/s
7.2
tokens/s
25.18
sec
pp1024+tg1024
83
tokens/s
7.2
tokens/s
12.46
sec
pp1280+tg3072
84
tokens/s
6.8
tokens/s
15.32
sec
pp384+tg1152
77
tokens/s
7.1
tokens/s
5.12
sec
pp64+tg1024
65
tokens/s
7.0
tokens/s
1.12
sec
pp16+tg1536
28
tokens/s
6.9
tokens/s
704
ms