sajibsrs/raging1.0-0.5B-MLX-4bit

Summarization·sajibsrs· 30

mlx apache-2.0 Summarization 77.3M params base_model:Qwen/Qwen2.5-0.5B-Instructbase_model:quantized:Qwen/Qwen2.5-0.5B-Instruct

A lightweight 494M parameter model fine-tuned specifically for RAG ingestion pipelines. Optimized for Apple Silicon via MLX 4-bit quantization.

# pull & run locally
pip install mlforge-sdk && mlforge pull sajibsrs/raging1.0-0.5B-MLX-4bit

Model details

Task

Summarization

Provider

sajibsrs

Framework

mlx

Parameters

77.3M

Size

276 MB

License

apache-2.0

Downloads

Updated

2026-06-25

A lightweight 494M parameter model fine-tuned specifically for RAG ingestion pipelines. Optimized for Apple Silicon via MLX 4-bit quantization.