TEST #1311 RESULTS
08/05/2025 - 10:32 AM
ACCELERATOR
MODEL
11.7
tokens/s
generation
10.62
sec
time to first token
112
tokens/s
prompt
50
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Max 8P+2E
RAM
64GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:29 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
143
tokens/s
15.2
tokens/s
7.25
sec
pp4096+tg256
131
tokens/s
10.9
tokens/s
31.43
sec
pp2048+tg256
133
tokens/s
12.4
tokens/s
15.46
sec
pp2048+tg768
125
tokens/s
10.9
tokens/s
16.50
sec
pp1024+tg1024
114
tokens/s
10.7
tokens/s
9.07
sec
pp1280+tg3072
117
tokens/s
10.1
tokens/s
11.04
sec
pp384+tg1152
110
tokens/s
11.8
tokens/s
3.57
sec
pp64+tg1024
98
tokens/s
12.1
tokens/s
717
ms
pp16+tg1536
35
tokens/s
11.4
tokens/s
519
ms