TEST #503 RESULTS
04/07/2025 - 4:16 PM
ACCELERATOR
MODEL
60.0
tokens/s
generation
1.55
sec
time to first token
835
tokens/s
prompt
318
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:23:36 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1015
tokens/s
69.9
tokens/s
1.02
sec
pp4096+tg256
749
tokens/s
39.7
tokens/s
5.49
sec
pp2048+tg256
920
tokens/s
54.1
tokens/s
2.24
sec
pp2048+tg768
898
tokens/s
50.4
tokens/s
2.30
sec
pp1024+tg1024
992
tokens/s
61.0
tokens/s
1.05
sec
pp1280+tg3072
986
tokens/s
48.0
tokens/s
1.31
sec
pp384+tg1152
1018
tokens/s
69.5
tokens/s
389
ms
pp64+tg1024
694
tokens/s
75.5
tokens/s
105
ms
pp16+tg1536
245
tokens/s
72.1
tokens/s
77
ms