TEST #3127 RESULTS
03/20/2026 - 10:41 AM
ACCELERATOR
MODEL
16.5
tokens/s
generation
8.49
sec
time to first token
150
tokens/s
prompt
66
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
25.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.3.0: Wed Jan 28 20:51:28 PST 2026; root:xnu-12377.91.3~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
174
tokens/s
18.0
tokens/s
5.95
sec
pp4096+tg256
156
tokens/s
12.5
tokens/s
26.31
sec
pp2048+tg256
155
tokens/s
15.7
tokens/s
13.27
sec
pp2048+tg768
153
tokens/s
15.2
tokens/s
13.42
sec
pp1024+tg1024
165
tokens/s
16.6
tokens/s
6.28
sec
pp1280+tg3072
161
tokens/s
14.8
tokens/s
8.00
sec
pp384+tg1152
163
tokens/s
18.0
tokens/s
2.41
sec
pp64+tg1024
156
tokens/s
19.0
tokens/s
462
ms
pp16+tg1536
69
tokens/s
18.8
tokens/s
280
ms
