TEST #870 RESULTS
05/14/2025 - 10:07 PM
ACCELERATOR
MODEL
82.5
tokens/s
generation
667
ms
time to first token
1817
tokens/s
prompt
608
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 0.6B Instruct - Q8_0
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
32GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:47 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2406
tokens/s
94.0
tokens/s
436
ms
pp4096+tg256
1805
tokens/s
54.6
tokens/s
2.29
sec
pp2048+tg256
2194
tokens/s
74.6
tokens/s
947
ms
pp2048+tg768
2191
tokens/s
71.3
tokens/s
948
ms
pp1024+tg1024
2332
tokens/s
84.2
tokens/s
450
ms
pp1280+tg3072
2286
tokens/s
66.7
tokens/s
571
ms
pp384+tg1152
1984
tokens/s
94.9
tokens/s
203
ms
pp64+tg1024
952
tokens/s
104
tokens/s
76
ms
pp16+tg1536
199
tokens/s
98.9
tokens/s
89
ms