This is Qwen/Qwen3-4B quantized with AutoRound in 4-bit (symmetric + gptq format). The model has been created, tested, and evaluated by The Kaitchup. The model is compatible with vLLM and Transformers.

More details in this article: How Well Does Qwen3 Handle 4-bit and 2-bit Quantization?

Developed by: The Kaitchup
License: Apache 2.0 license

How to Support My Work

Subscribe to The Kaitchup. This helps me a lot to continue quantizing and evaluating models for free.

Downloads last month: 864

Safetensors

Model size

876M params

Tensor type

I32

BF16

FP16

Inference Providers NEW

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

Model tree for kaitchup/Qwen3-4B-autoround-4bit-gptq

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(86)

this model

Collection including kaitchup/Qwen3-4B-autoround-4bit-gptq

Quantized Qwen3

Collection

13 items • Updated 7 days ago • 1