TEST #1692 RESULTS
10/22/2025 - 7:31 AM
ACCELERATOR
MODEL
10.9
tokens/s
generation
10.95
sec
time to first token
116
tokens/s
prompt
49
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 8P+4E
RAM
24GB
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
176
tokens/s
18.1
tokens/s
5.87
sec
pp4096+tg256
157
tokens/s
11.5
tokens/s
26.12
sec
pp2048+tg256
100
tokens/s
8.7
tokens/s
20.56
sec
pp2048+tg768
102
tokens/s
9.2
tokens/s
20.12
sec
pp1024+tg1024
99
tokens/s
9.6
tokens/s
10.43
sec
pp1280+tg3072
115
tokens/s
8.8
tokens/s
11.17
sec
pp384+tg1152
120
tokens/s
9.8
tokens/s
3.27
sec
pp64+tg1024
116
tokens/s
10.8
tokens/s
630
ms
pp16+tg1536
59
tokens/s
11.9
tokens/s
337
ms
