manu02/Qwen3-4B-Instruct-2507-bnb-4bit-nf4-dq

Qwen3-4B-Instruct-2507 (Quantized)

Description

This model is a 4-bit quantized version of the original Qwen/Qwen3-4B-Instruct-2507 model, optimized for reduced memory usage while maintaining performance.

Quantization Details

• Quantization Type: 4-bit
• bnb_4bit_quant_type: nf4
• bnb_4bit_use_double_quant: True
• bnb_4bit_compute_dtype: bfloat16
• bnb_4bit_quant_storage: uint8
• Original Footprint: 8044.94 MB (BFLOAT16)
• Quantized Footprint: 2594.96 MB (UINT8)
• Memory Reduction: 67.7%

Usage

from transformers import AutoModel, AutoTokenizer

model_name = "Qwen3-4B-Instruct-2507-bnb-4bit-nf4"
model = AutoModel.from_pretrained(
    "manu02/Qwen3-4B-Instruct-2507-bnb-4bit-nf4",
)
tokenizer = AutoTokenizer.from_pretrained("manu02/Qwen3-4B-Instruct-2507-bnb-4bit-nf4", use_fast=True)