TEST #950 RESULTS
05/27/2025 - 11:49 PM
ACCELERATOR
MODEL
38.6
tokens/s
generation
2.43
sec
time to first token
536
tokens/s
prompt
204
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
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:06 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T8103
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
639
tokens/s
43.4
tokens/s
1.62
sec
pp4096+tg256
478
tokens/s
25.2
tokens/s
8.61
sec
pp2048+tg256
587
tokens/s
35.0
tokens/s
3.51
sec
pp2048+tg768
586
tokens/s
33.6
tokens/s
3.53
sec
pp1024+tg1024
630
tokens/s
39.5
tokens/s
1.65
sec
pp1280+tg3072
629
tokens/s
31.2
tokens/s
2.06
sec
pp384+tg1152
643
tokens/s
44.8
tokens/s
616
ms
pp64+tg1024
465
tokens/s
48.7
tokens/s
155
ms
pp16+tg1536
171
tokens/s
45.9
tokens/s
111
ms