TEST #1807 RESULTS
11/16/2025 - 9:17 AM
ACCELERATOR
MODEL
165
tokens/s
generation
361
ms
time to first token
3316
tokens/s
prompt
1150
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 10P+4E
RAM
36GB
OS
Darwin
Kernel Release
25.2.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 25.2.0: Sat Nov 1 18:07:34 PDT 2025; root:xnu-12377.60.50.0.2~95/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4202
tokens/s
186
tokens/s
249
ms
pp4096+tg256
3494
tokens/s
118
tokens/s
1.18
sec
pp2048+tg256
3865
tokens/s
157
tokens/s
536
ms
pp2048+tg768
4005
tokens/s
147
tokens/s
518
ms
pp1024+tg1024
4181
tokens/s
167
tokens/s
250
ms
pp1280+tg3072
3943
tokens/s
138
tokens/s
330
ms
pp384+tg1152
3480
tokens/s
185
tokens/s
115
ms
pp64+tg1024
2059
tokens/s
200
tokens/s
36
ms
pp16+tg1536
612
tokens/s
192
tokens/s
31
ms