TEST #1750 RESULTS
11/07/2025 - 11:15 PM
ACCELERATOR
MODEL
11.2
tokens/s
generation
9.11
sec
time to first token
141
tokens/s
prompt
56
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
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Aug 11 21:16:31 PDT 2025; root:xnu-11417.140.69.701.11~1/RELEASE_ARM64_T6030
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
166
tokens/s
12.1
tokens/s
6.29
sec
pp4096+tg256
142
tokens/s
9.3
tokens/s
28.94
sec
pp2048+tg256
151
tokens/s
10.6
tokens/s
13.67
sec
pp2048+tg768
142
tokens/s
10.8
tokens/s
14.49
sec
pp1024+tg1024
145
tokens/s
11.4
tokens/s
7.15
sec
pp1280+tg3072
158
tokens/s
10.1
tokens/s
8.18
sec
pp384+tg1152
167
tokens/s
12.1
tokens/s
2.37
sec
pp64+tg1024
144
tokens/s
12.7
tokens/s
520
ms
pp16+tg1536
56
tokens/s
11.8
tokens/s
364
ms