TEST #888 RESULTS
05/16/2025 - 4:43 PM
ACCELERATOR
MODEL
69.2
tokens/s
generation
1.23
sec
time to first token
964
tokens/s
prompt
379
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 6P+2E
RAM
16GB
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 19:54:49 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1190
tokens/s
77.2
tokens/s
873
ms
pp4096+tg256
1019
tokens/s
44.6
tokens/s
4.05
sec
pp2048+tg256
1155
tokens/s
61.6
tokens/s
1.79
sec
pp2048+tg768
1191
tokens/s
60.4
tokens/s
1.73
sec
pp1024+tg1024
1155
tokens/s
71.2
tokens/s
899
ms
pp1280+tg3072
1192
tokens/s
56.2
tokens/s
1.09
sec
pp384+tg1152
1066
tokens/s
79.4
tokens/s
370
ms
pp64+tg1024
506
tokens/s
88.3
tokens/s
136
ms
pp16+tg1536
203
tokens/s
83.7
tokens/s
88
ms