TEST #1679 RESULTS
10/18/2025 - 7:29 PM
ACCELERATOR
MODEL
91.5
tokens/s
generation
899
ms
time to first token
1341
tokens/s
prompt
515
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M2 Pro 6P+4E
RAM
16GB
OS
Darwin
Kernel Release
24.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:30 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6020
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1635
tokens/s
104
tokens/s
636
ms
pp4096+tg256
1398
tokens/s
60.3
tokens/s
2.95
sec
pp2048+tg256
1560
tokens/s
82.0
tokens/s
1.33
sec
pp2048+tg768
1572
tokens/s
78.8
tokens/s
1.31
sec
pp1024+tg1024
1596
tokens/s
93.0
tokens/s
651
ms
pp1280+tg3072
1603
tokens/s
74.0
tokens/s
809
ms
pp384+tg1152
1496
tokens/s
106
tokens/s
265
ms
pp64+tg1024
940
tokens/s
116
tokens/s
76
ms
pp16+tg1536
264
tokens/s
110
tokens/s
69
ms