TEST #646 RESULTS
04/09/2025 - 5:26 PM
ACCELERATOR
MODEL
59.9
tokens/s
generation
1.56
sec
time to first token
827
tokens/s
prompt
317
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Wed Mar 19 21:18:03 PDT 2025; root:xnu-11417.101.15~1/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1009
tokens/s
68.3
tokens/s
1.03
sec
pp4096+tg256
743
tokens/s
39.3
tokens/s
5.54
sec
pp2048+tg256
915
tokens/s
53.9
tokens/s
2.26
sec
pp2048+tg768
913
tokens/s
51.5
tokens/s
2.26
sec
pp1024+tg1024
1001
tokens/s
60.6
tokens/s
1.04
sec
pp1280+tg3072
983
tokens/s
47.8
tokens/s
1.32
sec
pp384+tg1152
981
tokens/s
69.3
tokens/s
404
ms
pp64+tg1024
650
tokens/s
75.9
tokens/s
110
ms
pp16+tg1536
249
tokens/s
72.1
tokens/s
76
ms