TEST #1914 RESULTS
12/07/2025 - 2:48 PM
ACCELERATOR
MODEL
148
tokens/s
generation
350
ms
time to first token
3403
tokens/s
prompt
1130
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
24.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.2.0: Fri Dec 6 19:02:12 PST 2024; root:xnu-11215.61.5~2/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4250
tokens/s
168
tokens/s
247
ms
pp4096+tg256
3619
tokens/s
100
tokens/s
1.14
sec
pp2048+tg256
4116
tokens/s
135
tokens/s
505
ms
pp2048+tg768
4102
tokens/s
129
tokens/s
507
ms
pp1024+tg1024
4212
tokens/s
151
tokens/s
249
ms
pp1280+tg3072
4162
tokens/s
122
tokens/s
314
ms
pp384+tg1152
3790
tokens/s
170
tokens/s
107
ms
pp64+tg1024
1889
tokens/s
185
tokens/s
39
ms
pp16+tg1536
489
tokens/s
176
tokens/s
38
ms