TEST #562 RESULTS

04/08/2025 - 6:48 AM

6.3

tokens/s

generation

17.71

sec

time to first token

67

tokens/s

prompt

29

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M3 4P+4E
RAM
24GB
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 21:18:00 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
92
tokens/s
9.2
tokens/s
11.24
sec
pp4096+tg256
76
tokens/s
6.7
tokens/s
53.80
sec
pp2048+tg256
75
tokens/s
7.0
tokens/s
27.47
sec
pp2048+tg768
75
tokens/s
6.0
tokens/s
27.61
sec
pp1024+tg1024
76
tokens/s
6.1
tokens/s
13.57
sec
pp1280+tg3072
73
tokens/s
5.4
tokens/s
17.55
sec
pp384+tg1152
66
tokens/s
5.4
tokens/s
5.93
sec
pp64+tg1024
45
tokens/s
5.6
tokens/s
1.53
sec
pp16+tg1536
27
tokens/s
5.4
tokens/s
717
ms