TEST #166 RESULTS
03/30/2025 - 8:05 PM
ACCELERATOR
MODEL
169
tokens/s
generation
371
ms
time to first token
3211
tokens/s
prompt
1136
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
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Nov 14 18:15:21 PST 2024; root:xnu-11215.41.3~13/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4093
tokens/s
192
tokens/s
255
ms
pp4096+tg256
3384
tokens/s
117
tokens/s
1.22
sec
pp2048+tg256
3892
tokens/s
154
tokens/s
532
ms
pp2048+tg768
3842
tokens/s
149
tokens/s
539
ms
pp1024+tg1024
3949
tokens/s
173
tokens/s
265
ms
pp1280+tg3072
3844
tokens/s
140
tokens/s
339
ms
pp384+tg1152
3451
tokens/s
192
tokens/s
116
ms
pp64+tg1024
1864
tokens/s
207
tokens/s
39
ms
pp16+tg1536
583
tokens/s
198
tokens/s
32
ms