TEST #848 RESULTS
05/10/2025 - 6:29 AM
ACCELERATOR
MODEL
57.0
tokens/s
generation
1.58
sec
time to first token
831
tokens/s
prompt
311
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: Fri Apr 11 18:33:46 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1002
tokens/s
63.0
tokens/s
1.04
sec
pp4096+tg256
731
tokens/s
38.0
tokens/s
5.63
sec
pp2048+tg256
902
tokens/s
52.1
tokens/s
2.29
sec
pp2048+tg768
902
tokens/s
49.5
tokens/s
2.29
sec
pp1024+tg1024
995
tokens/s
58.5
tokens/s
1.04
sec
pp1280+tg3072
976
tokens/s
46.5
tokens/s
1.33
sec
pp384+tg1152
997
tokens/s
65.8
tokens/s
398
ms
pp64+tg1024
738
tokens/s
72.1
tokens/s
98
ms
pp16+tg1536
239
tokens/s
67.8
tokens/s
78
ms