TEST #779 RESULTS
04/27/2025 - 10:51 PM
ACCELERATOR
MODEL
72.5
tokens/s
generation
1.32
sec
time to first token
950
tokens/s
prompt
374
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
32GB
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 18:32:05 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1187
tokens/s
81.8
tokens/s
875
ms
pp4096+tg256
897
tokens/s
52.9
tokens/s
4.58
sec
pp2048+tg256
1080
tokens/s
68.4
tokens/s
1.91
sec
pp2048+tg768
1077
tokens/s
66.1
tokens/s
1.92
sec
pp1024+tg1024
1164
tokens/s
75.5
tokens/s
892
ms
pp1280+tg3072
1136
tokens/s
61.1
tokens/s
1.14
sec
pp384+tg1152
1089
tokens/s
80.7
tokens/s
365
ms
pp64+tg1024
709
tokens/s
86.5
tokens/s
101
ms
pp16+tg1536
214
tokens/s
79.7
tokens/s
85
ms