TEST #751 RESULTS
04/21/2025 - 2:37 PM
ACCELERATOR
MODEL
146
tokens/s
generation
358
ms
time to first token
3292
tokens/s
prompt
1104
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M3 Max 12P+4E
RAM
128GB
OS
Darwin
Kernel Release
24.4.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.4.0: Fri Apr 11 18:33:40 PDT 2025; root:xnu-11417.101.15~117/RELEASE_ARM64_T6031
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4228
tokens/s
164
tokens/s
248
ms
pp4096+tg256
3576
tokens/s
99.5
tokens/s
1.16
sec
pp2048+tg256
4063
tokens/s
134
tokens/s
511
ms
pp2048+tg768
3965
tokens/s
128
tokens/s
524
ms
pp1024+tg1024
4120
tokens/s
149
tokens/s
255
ms
pp1280+tg3072
3964
tokens/s
120
tokens/s
329
ms
pp384+tg1152
3806
tokens/s
167
tokens/s
106
ms
pp64+tg1024
1551
tokens/s
182
tokens/s
46
ms
pp16+tg1536
355
tokens/s
174
tokens/s
50
ms