TEST #973 RESULTS
06/02/2025 - 11:31 AM
ACCELERATOR
MODEL
43.1
tokens/s
generation
1.64
sec
time to first token
725
tokens/s
prompt
267
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
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:26 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1001
tokens/s
67.0
tokens/s
1.04
sec
pp4096+tg256
731
tokens/s
38.5
tokens/s
5.63
sec
pp2048+tg256
897
tokens/s
52.5
tokens/s
2.30
sec
pp2048+tg768
889
tokens/s
50.2
tokens/s
2.32
sec
pp1024+tg1024
986
tokens/s
58.7
tokens/s
1.05
sec
pp1280+tg3072
967
tokens/s
37.1
tokens/s
1.34
sec
pp384+tg1152
539
tokens/s
23.1
tokens/s
736
ms
pp64+tg1024
374
tokens/s
31.8
tokens/s
192
ms
pp16+tg1536
144
tokens/s
28.9
tokens/s
131
ms