TEST #1141 RESULTS
06/28/2025 - 7:51 AM
ACCELERATOR
MODEL
52.9
tokens/s
generation
1.82
sec
time to first token
710
tokens/s
prompt
274
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
8GB
OS
Darwin
Kernel Release
24.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:26 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
839
tokens/s
60.4
tokens/s
1.24
sec
pp4096+tg256
651
tokens/s
33.6
tokens/s
6.32
sec
pp2048+tg256
778
tokens/s
47.1
tokens/s
2.65
sec
pp2048+tg768
779
tokens/s
44.9
tokens/s
2.65
sec
pp1024+tg1024
838
tokens/s
53.8
tokens/s
1.24
sec
pp1280+tg3072
824
tokens/s
41.8
tokens/s
1.57
sec
pp384+tg1152
817
tokens/s
61.5
tokens/s
484
ms
pp64+tg1024
651
tokens/s
68.2
tokens/s
111
ms
pp16+tg1536
210
tokens/s
64.5
tokens/s
89
ms