woctordho
/

Qwen3-30B-A3B-fused-bnb-4bit

Text Generation

4-bit precision

Model card Files Files and versions

See https://github.com/woct0rdho/transformers-qwen3-moe-fused

Downloads last month: 3,050

Safetensors

Model size

16B params

Tensor type

F32

·

BF16

·

U8

·

Inference Providers NEW

Text Generation

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

Model tree for woctordho/Qwen3-30B-A3B-fused-bnb-4bit

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

Qwen/Qwen3-30B-A3B

Quantized

(92)

this model