TEST #3525 RESULTS
05/14/2026 - 8:49 AM
ACCELERATOR
MODEL
9.4
tokens/s
generation
13.73
sec
time to first token
94
tokens/s
prompt
40
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
24GB
OS
Darwin
Kernel Release
25.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.4.0: Thu Mar 19 19:31:09 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
105
tokens/s
10.1
tokens/s
9.83
sec
pp4096+tg256
93
tokens/s
7.8
tokens/s
44.31
sec
pp2048+tg256
100
tokens/s
9.1
tokens/s
20.64
sec
pp2048+tg768
99
tokens/s
9.1
tokens/s
20.82
sec
pp1024+tg1024
103
tokens/s
9.7
tokens/s
10.01
sec
pp1280+tg3072
100
tokens/s
8.8
tokens/s
12.93
sec
pp384+tg1152
103
tokens/s
10.1
tokens/s
3.84
sec
pp64+tg1024
97
tokens/s
10.2
tokens/s
749
ms
pp16+tg1536
43
tokens/s
10.0
tokens/s
480
ms
