TEST #1053 RESULTS
06/14/2025 - 3:12 PM
ACCELERATOR
MODEL
99.3
tokens/s
generation
803
ms
time to first token
1495
tokens/s
prompt
570
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
1855
tokens/s
113
tokens/s
561
ms
pp4096+tg256
1556
tokens/s
67.2
tokens/s
2.65
sec
pp2048+tg256
1768
tokens/s
90.5
tokens/s
1.17
sec
pp2048+tg768
1766
tokens/s
86.7
tokens/s
1.17
sec
pp1024+tg1024
1810
tokens/s
102
tokens/s
575
ms
pp1280+tg3072
1792
tokens/s
81.4
tokens/s
724
ms
pp384+tg1152
1678
tokens/s
113
tokens/s
237
ms
pp64+tg1024
978
tokens/s
123
tokens/s
73
ms
pp16+tg1536
257
tokens/s
117
tokens/s
69
ms