TEST #1479 RESULTS
09/05/2025 - 3:55 AM
ACCELERATOR
MODEL
109
tokens/s
generation
508
ms
time to first token
2585
tokens/s
prompt
821
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
64GB
OS
Darwin
Kernel Release
23.6.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 23.6.0: Thu Sep 12 23:36:23 PDT 2024; root:xnu-10063.141.1.701.1~1/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2907
tokens/s
115
tokens/s
362
ms
pp4096+tg256
2314
tokens/s
82.9
tokens/s
1.79
sec
pp2048+tg256
2836
tokens/s
105
tokens/s
733
ms
pp2048+tg768
2705
tokens/s
100
tokens/s
769
ms
pp1024+tg1024
3688
tokens/s
112
tokens/s
284
ms
pp1280+tg3072
2971
tokens/s
93.7
tokens/s
443
ms
pp384+tg1152
3639
tokens/s
120
tokens/s
111
ms
pp64+tg1024
1742
tokens/s
127
tokens/s
42
ms
pp16+tg1536
464
tokens/s
122
tokens/s
40
ms