TEST #1862 RESULTS
11/24/2025 - 11:25 PM
ACCELERATOR
MODEL
99.5
tokens/s
generation
809
ms
time to first token
1458
tokens/s
prompt
564
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 8P+4E
RAM
16GB
OS
Darwin
Kernel Release
25.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.1.0: Mon Oct 20 19:33:00 PDT 2025; root:xnu-12377.41.6~2/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1849
tokens/s
115
tokens/s
563
ms
pp4096+tg256
1548
tokens/s
67.7
tokens/s
2.66
sec
pp2048+tg256
1766
tokens/s
90.8
tokens/s
1.17
sec
pp2048+tg768
1759
tokens/s
87.5
tokens/s
1.18
sec
pp1024+tg1024
1820
tokens/s
102
tokens/s
572
ms
pp1280+tg3072
1802
tokens/s
80.7
tokens/s
720
ms
pp384+tg1152
1637
tokens/s
112
tokens/s
242
ms
pp64+tg1024
734
tokens/s
122
tokens/s
94
ms
pp16+tg1536
206
tokens/s
117
tokens/s
85
ms