This quantization was uploaded on 2026-10-13 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3-Reranker-0.6B-oQ8e

This model was quantized using oQ (oMLX v0.7.1.dev1) mixed-precision quantization.

Quantization details

Model type: qwen3
Bits: 8
Group size: 64
Format: MLX safetensors

Downloads last month: 125

Safetensors

Model size

0.6B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for scottlowry/Qwen3-Reranker-0.6B-oQ8e

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-Reranker-0.6B

Quantized

(90)

this model