TEST #1114 RESULTS
06/25/2025 - 2:37 PM
ACCELERATOR
MODEL
150
tokens/s
generation
348
ms
time to first token
3395
tokens/s
prompt
1134
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
48GB
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 19:52:00 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4328
tokens/s
182
tokens/s
242
ms
pp4096+tg256
3662
tokens/s
101
tokens/s
1.13
sec
pp2048+tg256
4117
tokens/s
135
tokens/s
505
ms
pp2048+tg768
4093
tokens/s
129
tokens/s
508
ms
pp1024+tg1024
4232
tokens/s
151
tokens/s
248
ms
pp1280+tg3072
4133
tokens/s
121
tokens/s
316
ms
pp384+tg1152
3708
tokens/s
168
tokens/s
109
ms
pp64+tg1024
1725
tokens/s
184
tokens/s
42
ms
pp16+tg1536
558
tokens/s
175
tokens/s
33
ms