TEST #1177 RESULTS
07/04/2025 - 7:03 PM
ACCELERATOR
MODEL
18.2
tokens/s
generation
6.82
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
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
217
tokens/s
19.8
tokens/s
4.77
sec
pp4096+tg256
192
tokens/s
13.8
tokens/s
21.42
sec
pp2048+tg256
195
tokens/s
17.1
tokens/s
10.55
sec
pp2048+tg768
194
tokens/s
16.6
tokens/s
10.63
sec
pp1024+tg1024
203
tokens/s
18.5
tokens/s
5.10
sec
pp1280+tg3072
202
tokens/s
15.9
tokens/s
6.40
sec
pp384+tg1152
211
tokens/s
20.3
tokens/s
1.87
sec
pp64+tg1024
188
tokens/s
21.2
tokens/s
384
ms
pp16+tg1536
78
tokens/s
20.3
tokens/s
250
ms