starkdmi
/

Qwen3-Embedding-0.6B-mlx-5bit

Feature Extraction

Model card Files Files and versions

5-bit MLX conversion of Qwen/Qwen3-Embedding-0.6B, licensed under Apache-2.0 as the original.

Downloads last month: 163

Safetensors

Model size

0.6B params

Tensor type

U32

·

F16

·

MLX

Hardware compatibility

Log In to add your hardware

Quantized

Model tree for starkdmi/Qwen3-Embedding-0.6B-mlx-5bit

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-Embedding-0.6B

Finetuned

(584)

this model