Packages

bumblebee_quantized

0.1.0

4-bit quantized LLM inference with LoRA adapters for Apple Silicon

HexDocs

Current section

Files

Jump to

Readme 1 Version 5 Dependencies Dependants Files Activity

bumblebee_quantized CHANGELOG.md

Raw

CHANGELOG.md

# 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

Operator	Description	Example
name:	Match package name. Supports * wildcards and repo/package form	name:phx* or name:hexpm/phoenix
description:	Full-text search of package descriptions	description:auth
depends:	Packages depending on a given package. Supports repo:package form	depends:ecto or depends:hexpm:ecto
build_tool:	Filter by build tool	build_tool:mix
updated_after:	Packages updated after an ISO8601 datetime	updated_after:2025-01-01T00:00:00Z
extra:	Match custom metadata (key,value). Nested keys are separated by commas	extra:license,MIT