TEST #2912 RESULTS

02/27/2026 - 1:43 AM

11.1

tokens/s

generation

11.83

sec

time to first token

109

tokens/s

prompt

47

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
115
tokens/s
10.8
tokens/s
8.95
sec
pp4096+tg256
105
tokens/s
9.4
tokens/s
39.12
sec
pp2048+tg256
118
tokens/s
10.6
tokens/s
17.44
sec
pp2048+tg768
118
tokens/s
10.4
tokens/s
17.46
sec
pp1024+tg1024
122
tokens/s
11.2
tokens/s
8.49
sec
pp1280+tg3072
120
tokens/s
10.5
tokens/s
10.79
sec
pp384+tg1152
123
tokens/s
12.2
tokens/s
3.20
sec
pp64+tg1024
113
tokens/s
12.6
tokens/s
642
ms
pp16+tg1536
50
tokens/s
12.4
tokens/s
393
ms