TEST #1527 RESULTS
09/16/2025 - 12:17 PM
ACCELERATOR
MODEL
18.0
tokens/s
generation
6.56
sec
time to first token
192
tokens/s
prompt
81
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
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:54 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
214
tokens/s
19.8
tokens/s
4.84
sec
pp4096+tg256
195
tokens/s
13.6
tokens/s
21.11
sec
pp2048+tg256
209
tokens/s
17.1
tokens/s
9.86
sec
pp2048+tg768
210
tokens/s
16.5
tokens/s
9.80
sec
pp1024+tg1024
216
tokens/s
18.4
tokens/s
4.80
sec
pp1280+tg3072
210
tokens/s
15.8
tokens/s
6.16
sec
pp384+tg1152
212
tokens/s
19.8
tokens/s
1.86
sec
pp64+tg1024
189
tokens/s
21.0
tokens/s
382
ms
pp16+tg1536
75
tokens/s
20.4
tokens/s
257
ms
