TEST #778 RESULTS

04/27/2025 - 10:10 PM

8.0

tokens/s

generation

17.30

sec

time to first token

71

tokens/s

prompt

32

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M4 4P+6E
RAM
32GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:32:05 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
90
tokens/s
10.1
tokens/s
11.51
sec
pp4096+tg256
78
tokens/s
7.5
tokens/s
52.79
sec
pp2048+tg256
82
tokens/s
8.3
tokens/s
25.23
sec
pp2048+tg768
76
tokens/s
7.6
tokens/s
27.17
sec
pp1024+tg1024
75
tokens/s
7.8
tokens/s
13.75
sec
pp1280+tg3072
72
tokens/s
7.0
tokens/s
17.91
sec
pp384+tg1152
70
tokens/s
7.9
tokens/s
5.57
sec
pp64+tg1024
63
tokens/s
8.2
tokens/s
1.13
sec
pp16+tg1536
30
tokens/s
7.8
tokens/s
641
ms