PyPI page
Home page
Author:
None
License:
MIT
Summary:
Run AI models too large for your Mac's memory — expert caching, speculative execution, and 15+ research techniques for MoE inference on Apple Silicon
Latest version:
0.6.1
Required dependencies:
huggingface-hub
|
mlx
|
mlx-lm
|
numpy
|
psutil
|
safetensors
|
tabulate
Optional dependencies:
lz4
|
mlx-flash
|
pytest
|
pytest-benchmark
|
pytest-cov
|
zstandard
Downloads last day:
4
Downloads last week:
57
Downloads last month:
325