TEST #3560 RESULTS
05/17/2026 - 7:24 PM
ACCELERATOR
MODEL
12.2
tokens/s
generation
10.67
sec
time to first token
120
tokens/s
prompt
52
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Pro 5P+6E
RAM
18GB
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 19:31:56 PDT 2026; root:xnu-12377.101.15~1/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
132
tokens/s
13.0
tokens/s
7.84
sec
pp4096+tg256
119
tokens/s
10.0
tokens/s
34.66
sec
pp2048+tg256
129
tokens/s
11.7
tokens/s
16.01
sec
pp2048+tg768
129
tokens/s
11.5
tokens/s
16.02
sec
pp1024+tg1024
133
tokens/s
12.4
tokens/s
7.77
sec
pp1280+tg3072
132
tokens/s
11.1
tokens/s
9.79
sec
pp384+tg1152
134
tokens/s
13.1
tokens/s
2.95
sec
pp64+tg1024
122
tokens/s
13.5
tokens/s
594
ms
pp16+tg1536
51
tokens/s
13.3
tokens/s
383
ms