TEST #928 RESULTS
05/22/2025 - 7:08 AM
ACCELERATOR
MODEL
99.6
tokens/s
generation
811
ms
time to first token
1485
tokens/s
prompt
567
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 8P+4E
RAM
32GB
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 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1833
tokens/s
114
tokens/s
567
ms
pp4096+tg256
1524
tokens/s
67.1
tokens/s
2.70
sec
pp2048+tg256
1760
tokens/s
90.8
tokens/s
1.17
sec
pp2048+tg768
1768
tokens/s
87.0
tokens/s
1.17
sec
pp1024+tg1024
1808
tokens/s
101
tokens/s
576
ms
pp1280+tg3072
1791
tokens/s
81.5
tokens/s
724
ms
pp384+tg1152
1708
tokens/s
114
tokens/s
233
ms
pp64+tg1024
943
tokens/s
123
tokens/s
75
ms
pp16+tg1536
231
tokens/s
118
tokens/s
77
ms