TEST #3198 RESULTS
03/25/2026 - 8:26 PM
ACCELERATOR
MODEL
4.3
tokens/s
generation
28.78
sec
time to first token
46
tokens/s
prompt
19
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 4P+4E
RAM
16GB
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 21:03:25 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
48
tokens/s
4.2
tokens/s
21.41
sec
pp4096+tg256
41
tokens/s
3.8
tokens/s
99.34
sec
pp2048+tg256
51
tokens/s
4.1
tokens/s
40.14
sec
pp2048+tg768
46
tokens/s
4.2
tokens/s
44.58
sec
pp1024+tg1024
53
tokens/s
4.7
tokens/s
19.41
sec
pp1280+tg3072
53
tokens/s
4.1
tokens/s
24.40
sec
pp384+tg1152
54
tokens/s
4.6
tokens/s
7.24
sec
pp64+tg1024
45
tokens/s
4.6
tokens/s
1.56
sec
pp16+tg1536
20
tokens/s
4.5
tokens/s
958
ms
