TEST #8 RESULTS
03/19/2025 - 10:17 PM
ACCELERATOR
MODEL
156
tokens/s
generation
1.97
sec
time to first token
680
tokens/s
prompt
378
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 Max 12P+4E
RAM
128GB
OS
Darwin
Kernel Release
24.3.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.3.0: Thu Jan 2 20:24:22 PST 2025; root:xnu-11215.81.4~3/RELEASE_ARM64_T6041
RUNTIME
Name
llamafile
Version
0.9.1
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
856
tokens/s
186
tokens/s
1.20
sec
pp4096+tg256
674
tokens/s
145
tokens/s
6.08
sec
pp2048+tg256
703
tokens/s
157
tokens/s
2.92
sec
pp2048+tg768
653
tokens/s
152
tokens/s
3.14
sec
pp1024+tg1024
663
tokens/s
153
tokens/s
1.55
sec
pp1280+tg3072
632
tokens/s
132
tokens/s
2.03
sec
pp384+tg1152
607
tokens/s
159
tokens/s
642
ms
pp64+tg1024
728
tokens/s
165
tokens/s
94
ms
pp16+tg1536
602
tokens/s
158
tokens/s
31
ms