# Changelog

## v0.1.0 (2025-01-26)

Initial release.

### Features

- **BumblebeeQuantized.Loader** - Load 4-bit quantized models from MLX safetensors format
- **BumblebeeQuantized.Adapters** - Load, apply, and train LoRA adapters
- **BumblebeeQuantized.Serving** - Nx.Serving interface for text generation
- **BumblebeeQuantized.Training** - LoRA training workflow via mlx_lm
- **BumblebeeQuantized.Models.Qwen3** - Qwen3 quantized model definition

### Supported Models

- Qwen3 (8B tested, other sizes should work)

### Requirements

- Apple Silicon Mac (M1/M2/M3/M4)
- EMLX with quantization ops
- Bumblebee for tokenization