redairship
/

qwen3-embedding-4b-8bit-mlx

Model card Files Files and versions

redairship/qwen3-embedding-4b-8bit-mlx

MLX embedding model artifact published for iOS semantic retrieval.

Source model: Qwen/Qwen3-Embedding-4B
Source revision: main
Embedding dimension: 2560
Quantization: 8bit

This repo is published by the container-training Ops > Models workflow.

Downloads last month: 186

Safetensors

Model size

4B params

Tensor type

BF16

·

MLX

Hardware compatibility

Log In to add your hardware

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support