TEST #3662 RESULTS
06/01/2026 - 7:07 AM
ACCELERATOR
MODEL
12.3
tokens/s
generation
8.66
sec
time to first token
147
tokens/s
prompt
59
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Pro 6P+6E
RAM
18GB
OS
Darwin
Kernel Release
25.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.5.0: Mon Apr 27 20:41:06 PDT 2026; root:xnu-12377.121.6~2/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
163
tokens/s
13.0
tokens/s
6.36
sec
pp4096+tg256
146
tokens/s
10.1
tokens/s
28.19
sec
pp2048+tg256
158
tokens/s
12.0
tokens/s
13.01
sec
pp2048+tg768
160
tokens/s
11.5
tokens/s
12.91
sec
pp1024+tg1024
165
tokens/s
12.6
tokens/s
6.29
sec
pp1280+tg3072
163
tokens/s
11.3
tokens/s
7.91
sec
pp384+tg1152
166
tokens/s
13.0
tokens/s
2.39
sec
pp64+tg1024
149
tokens/s
13.6
tokens/s
503
ms
pp16+tg1536
54
tokens/s
13.4
tokens/s
367
ms
