TEST #1280 RESULTS
08/01/2025 - 3:04 AM
ACCELERATOR
MODEL
32.1
tokens/s
generation
62.00
sec
time to first token
52
tokens/s
prompt
30
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3-Coder-30B-A3B-Instruct - Q8_0
SYSTEM
CPU
Apple M4 Pro 10P+4E
RAM
64GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:40 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
21
tokens/s
36.3
tokens/s
49.21
sec
pp4096+tg256
21
tokens/s
21.8
tokens/s
197.83
sec
pp2048+tg256
21
tokens/s
29.4
tokens/s
98.63
sec
pp2048+tg768
21
tokens/s
28.1
tokens/s
98.61
sec
pp1024+tg1024
21
tokens/s
32.8
tokens/s
49.22
sec
pp1280+tg3072
24
tokens/s
26.4
tokens/s
53.21
sec
pp384+tg1152
36
tokens/s
36.6
tokens/s
10.77
sec
pp64+tg1024
174
tokens/s
39.4
tokens/s
392
ms
pp16+tg1536
130
tokens/s
37.9
tokens/s
147
ms