TEST #224 RESULTS
04/04/2025 - 4:10 AM
ACCELERATOR
MODEL
38.4
tokens/s
generation
2.40
sec
time to first token
540
tokens/s
prompt
205
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
634
tokens/s
44.0
tokens/s
1.64
sec
pp4096+tg256
487
tokens/s
24.9
tokens/s
8.45
sec
pp2048+tg256
593
tokens/s
34.7
tokens/s
3.48
sec
pp2048+tg768
594
tokens/s
33.6
tokens/s
3.48
sec
pp1024+tg1024
633
tokens/s
39.2
tokens/s
1.64
sec
pp1280+tg3072
637
tokens/s
30.9
tokens/s
2.03
sec
pp384+tg1152
652
tokens/s
44.7
tokens/s
608
ms
pp64+tg1024
464
tokens/s
48.4
tokens/s
155
ms
pp16+tg1536
171
tokens/s
45.4
tokens/s
111
ms