TEST #2009 RESULTS

12/21/2025 - 11:44 AM

7.0

tokens/s

generation

21.43

sec

time to first token

60

tokens/s

prompt

27

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M2 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:34 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
66
tokens/s
8.0
tokens/s
15.68
sec
pp4096+tg256
59
tokens/s
5.6
tokens/s
69.11
sec
pp2048+tg256
64
tokens/s
6.9
tokens/s
32.18
sec
pp2048+tg768
64
tokens/s
6.6
tokens/s
32.14
sec
pp1024+tg1024
63
tokens/s
6.7
tokens/s
16.26
sec
pp1280+tg3072
65
tokens/s
6.1
tokens/s
19.82
sec
pp384+tg1152
66
tokens/s
7.4
tokens/s
5.92
sec
pp64+tg1024
63
tokens/s
7.7
tokens/s
1.13
sec
pp16+tg1536
29
tokens/s
7.6
tokens/s
652
ms