TEST #1697 RESULTS

10/24/2025 - 11:02 PM

17.9

tokens/s

generation

7.08

sec

time to first token

180

tokens/s

prompt

77

LocalScore

HOW YOU STACK UP
Explore All Results

Qwen2.5 14B Instruct - Q4_K - Medium

SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Wed Sep 17 21:41:26 PDT 2025; root:xnu-12377.1.9~141/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
208
tokens/s
19.4
tokens/s
4.97
sec
pp4096+tg256
187
tokens/s
13.5
tokens/s
21.98
sec
pp2048+tg256
187
tokens/s
16.9
tokens/s
11.02
sec
pp2048+tg768
185
tokens/s
16.4
tokens/s
11.15
sec
pp1024+tg1024
193
tokens/s
18.3
tokens/s
5.36
sec
pp1280+tg3072
194
tokens/s
15.8
tokens/s
6.65
sec
pp384+tg1152
198
tokens/s
19.8
tokens/s
1.99
sec
pp64+tg1024
188
tokens/s
20.7
tokens/s
385
ms
pp16+tg1536
79
tokens/s
20.3
tokens/s
246
ms