TEST #2923 RESULTS

02/27/2026 - 12:39 PM

12.0

tokens/s

generation

11.44

sec

time to first token

111

tokens/s

prompt

49

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M5 4P+6E
RAM
32GB
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 21:09:49 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8142
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
123
tokens/s
12.3
tokens/s
8.44
sec
pp4096+tg256
112
tokens/s
10.2
tokens/s
36.76
sec
pp2048+tg256
119
tokens/s
11.5
tokens/s
17.30
sec
pp2048+tg768
119
tokens/s
11.4
tokens/s
17.29
sec
pp1024+tg1024
123
tokens/s
12.2
tokens/s
8.42
sec
pp1280+tg3072
122
tokens/s
11.2
tokens/s
10.56
sec
pp384+tg1152
123
tokens/s
12.7
tokens/s
3.20
sec
pp64+tg1024
112
tokens/s
13.1
tokens/s
644
ms
pp16+tg1536
51
tokens/s
12.9
tokens/s
388
ms