TEST #1960 RESULTS
12/17/2025 - 4:29 PM
ACCELERATOR
MODEL
17.5
tokens/s
generation
6.77
sec
time to first token
187
tokens/s
prompt
79
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
48GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Tue Nov 18 21:09:56 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
210
tokens/s
19.2
tokens/s
4.93
sec
pp4096+tg256
191
tokens/s
13.4
tokens/s
21.51
sec
pp2048+tg256
203
tokens/s
16.6
tokens/s
10.16
sec
pp2048+tg768
198
tokens/s
15.4
tokens/s
10.39
sec
pp1024+tg1024
204
tokens/s
17.9
tokens/s
5.07
sec
pp1280+tg3072
204
tokens/s
15.2
tokens/s
6.32
sec
pp384+tg1152
212
tokens/s
19.2
tokens/s
1.86
sec
pp64+tg1024
181
tokens/s
20.7
tokens/s
397
ms
pp16+tg1536
77
tokens/s
20.2
tokens/s
255
ms
