TEST #1546 RESULTS
09/23/2025 - 2:00 AM
ACCELERATOR
MODEL
40.6
tokens/s
generation
2.24
sec
time to first token
579
tokens/s
prompt
219
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
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:45 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
693
tokens/s
45.2
tokens/s
1.50
sec
pp4096+tg256
512
tokens/s
27.1
tokens/s
8.04
sec
pp2048+tg256
646
tokens/s
37.2
tokens/s
3.20
sec
pp2048+tg768
642
tokens/s
35.5
tokens/s
3.22
sec
pp1024+tg1024
693
tokens/s
41.3
tokens/s
1.50
sec
pp1280+tg3072
683
tokens/s
33.4
tokens/s
1.90
sec
pp384+tg1152
693
tokens/s
46.5
tokens/s
574
ms
pp64+tg1024
480
tokens/s
50.8
tokens/s
153
ms
pp16+tg1536
167
tokens/s
48.6
tokens/s
114
ms