alwoolley
/

Qwen3-4B-bnb-nf4

4-bit precision

Model card Files Files and versions

Qwen3-4B NF4 (4-Bit Double-Quantized)

4-bit NormalFloat4 double-quantized weights for Qwen/Qwen3-4B via bitsandbytes.

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

BF16

·

U8

·

Inference Providers NEW

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

Model tree for alwoolley/Qwen3-4B-bnb-nf4

Base model

Qwen/Qwen3-4B-Base

Finetuned

Quantized

(311)

this model