TEST #432 RESULTS
04/06/2025 - 9:38 PM
ACCELERATOR
MODEL
39.0
tokens/s
generation
2.31
sec
time to first token
578
tokens/s
prompt
214
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 4P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Oct 10 21:05:14 PDT 2024; root:xnu-11215.41.3~2/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
685
tokens/s
45.8
tokens/s
1.51
sec
pp4096+tg256
487
tokens/s
26.6
tokens/s
8.45
sec
pp2048+tg256
622
tokens/s
35.1
tokens/s
3.32
sec
pp2048+tg768
624
tokens/s
33.6
tokens/s
3.31
sec
pp1024+tg1024
684
tokens/s
39.7
tokens/s
1.52
sec
pp1280+tg3072
676
tokens/s
31.7
tokens/s
1.92
sec
pp384+tg1152
703
tokens/s
44.7
tokens/s
565
ms
pp64+tg1024
528
tokens/s
48.1
tokens/s
141
ms
pp16+tg1536
190
tokens/s
46.1
tokens/s
100
ms