TEST #854 RESULTS
05/11/2025 - 4:09 AM
ACCELERATOR
MODEL
53.9
tokens/s
generation
1.59
sec
time to first token
822
tokens/s
prompt
303
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 4P+4E
RAM
24GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:46 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T8112
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1002
tokens/s
65.5
tokens/s
1.04
sec
pp4096+tg256
730
tokens/s
37.9
tokens/s
5.64
sec
pp2048+tg256
903
tokens/s
51.7
tokens/s
2.29
sec
pp2048+tg768
904
tokens/s
49.4
tokens/s
2.29
sec
pp1024+tg1024
994
tokens/s
53.1
tokens/s
1.05
sec
pp1280+tg3072
924
tokens/s
44.0
tokens/s
1.40
sec
pp384+tg1152
1007
tokens/s
60.4
tokens/s
395
ms
pp64+tg1024
680
tokens/s
58.7
tokens/s
107
ms
pp16+tg1536
253
tokens/s
64.0
tokens/s
76
ms