TEST #876 RESULTS
05/14/2025 - 11:24 PM
ACCELERATOR
MODEL
47.5
tokens/s
generation
1.47
sec
time to first token
912
tokens/s
prompt
309
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen3 0.6B - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
23.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.3.0: Wed Dec 20 21:30:27 PST 2023; root:xnu-10002.81.5~7/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1121
tokens/s
54.6
tokens/s
932
ms
pp4096+tg256
746
tokens/s
30.5
tokens/s
5.52
sec
pp2048+tg256
998
tokens/s
42.8
tokens/s
2.08
sec
pp2048+tg768
999
tokens/s
40.8
tokens/s
2.07
sec
pp1024+tg1024
1128
tokens/s
48.7
tokens/s
926
ms
pp1280+tg3072
1104
tokens/s
38.0
tokens/s
1.18
sec
pp384+tg1152
1157
tokens/s
55.9
tokens/s
348
ms
pp64+tg1024
725
tokens/s
60.1
tokens/s
101
ms
pp16+tg1536
227
tokens/s
56.3
tokens/s
83
ms