TEST #1027 RESULTS
06/11/2025 - 2:29 AM
ACCELERATOR
MODEL
63.7
tokens/s
generation
1.45
sec
time to first token
917
tokens/s
prompt
342
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 4P+4E
RAM
24GB
OS
Darwin
Kernel Release
23.5.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.5.0: Wed May 1 20:14:59 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T8122
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1069
tokens/s
66.1
tokens/s
972
ms
pp4096+tg256
787
tokens/s
44.8
tokens/s
5.23
sec
pp2048+tg256
992
tokens/s
59.2
tokens/s
2.08
sec
pp2048+tg768
972
tokens/s
56.7
tokens/s
2.12
sec
pp1024+tg1024
1071
tokens/s
65.0
tokens/s
971
ms
pp1280+tg3072
1067
tokens/s
53.7
tokens/s
1.21
sec
pp384+tg1152
1107
tokens/s
73.4
tokens/s
359
ms
pp64+tg1024
879
tokens/s
79.0
tokens/s
84
ms
pp16+tg1536
306
tokens/s
75.5
tokens/s
64
ms