TEST #1573 RESULTS
09/30/2025 - 6:49 AM
ACCELERATOR
MODEL
82.3
tokens/s
generation
999
ms
time to first token
1197
tokens/s
prompt
462
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M1 Pro 8P+2E
RAM
16GB
OS
Darwin
Kernel Release
25.0.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.0.0: Mon Aug 25 21:17:51 PDT 2025; root:xnu-12377.1.9~3/RELEASE_ARM64_T6000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1465
tokens/s
93.2
tokens/s
710
ms
pp4096+tg256
1260
tokens/s
54.4
tokens/s
3.27
sec
pp2048+tg256
1408
tokens/s
74.4
tokens/s
1.47
sec
pp2048+tg768
1414
tokens/s
71.0
tokens/s
1.46
sec
pp1024+tg1024
1444
tokens/s
83.8
tokens/s
720
ms
pp1280+tg3072
1439
tokens/s
66.6
tokens/s
901
ms
pp384+tg1152
1399
tokens/s
94.7
tokens/s
284
ms
pp64+tg1024
720
tokens/s
104
tokens/s
97
ms
pp16+tg1536
224
tokens/s
98.5
tokens/s
80
ms