TEST #2070 RESULTS
12/31/2025 - 8:06 AM
ACCELERATOR
MODEL
6.6
tokens/s
generation
22.21
sec
time to first token
56
tokens/s
prompt
26
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
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 21:08:48 PST 2025; root:xnu-12377.61.12~1/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
81
tokens/s
9.4
tokens/s
12.76
sec
pp4096+tg256
68
tokens/s
5.4
tokens/s
60.56
sec
pp2048+tg256
52
tokens/s
6.0
tokens/s
39.22
sec
pp2048+tg768
57
tokens/s
6.2
tokens/s
36.15
sec
pp1024+tg1024
60
tokens/s
6.0
tokens/s
17.28
sec
pp1280+tg3072
51
tokens/s
5.8
tokens/s
25.16
sec
pp384+tg1152
59
tokens/s
6.8
tokens/s
6.63
sec
pp64+tg1024
52
tokens/s
7.0
tokens/s
1.37
sec
pp16+tg1536
25
tokens/s
6.9
tokens/s
774
ms