What are the hardware requirements for Qwen1.5 32B Chat GPTQ Int4?

Qwen1.5 32B Chat GPTQ Int4 requires approximately 19.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen1.5 32B Chat GPTQ Int4 and how large is it?

Qwen1.5 32B Chat GPTQ Int4 is developed by Qwen, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen1.5 32B Chat GPTQ Int4?

Qwen1.5 32B Chat GPTQ Int4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen1.5 32B Chat GPTQ Int4 by Qwen — VRAM 19.5GB, 32K context

Name: Qwen1.5 32B Chat GPTQ Int4
Author: Qwen

Qwen1.5 32B Chat GPTQ Int4 is an open-source language model by Qwen. Features: 32b LLM, VRAM: 19.5GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.15.

Arxiv:2309.16609 4-bit Chat Conversational Deploy:azure En Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-32B-Chat-GPTQ-Int4

Qwen1.5 32B Chat GPTQ Int4 Parameters and Internals

Model Type

transformer-based, decoder-only, language model

Use Cases

Areas:

Research, Commercial applications

Applications:

Text generation, Chat models

Primary Use Cases:

Introduction to language models

Limitations:

Code switching

Additional Notes

Users are warned against deploying this model with vLLM temporarily and are instead advised to use the AWQ model.

Supported Languages

languages_supported (Multilingual), proficiency_levels (Both base and chat models support multiple languages)

Training Details

Data Volume:

a large amount of data

Methodology:

pretrained with both supervised finetuning and direct preference optimization

Context Length:

32768

Model Architecture:

Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention

Input Output

Input Format:

Expected structure is a list of message dictionaries containing 'role' and 'content'

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Use provided hyperparameters in generation_config.json to avoid issues like code switching

LLM Name	Qwen1.5 32B Chat GPTQ Int4
Repository 🤗	https://huggingface.co/Qwen/Qwen1.5-32B-Chat-GPTQ-Int4
Model Size	32b
Required VRAM	19.5 GB
Updated	2026-08-06
Maintainer	Qwen
Model Type	qwen2
Model Files	4.0 GB: 1-of-5 4.0 GB: 2-of-5 4.0 GB: 3-of-5 4.0 GB: 4-of-5 3.5 GB: 5-of-5
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	float16
Errors	replace

Rank the Qwen1.5 32B Chat GPTQ Int4 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen1.5 32B Chat GPTQ Int4

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 32B Instruct GPTQ Int4	32K / 19.5 GB	478520	40
Qwen2.5 32B Instruct GPTQ Int8	32K / 35.1 GB	121583	14
...5 Coder 32B Instruct GPTQ Int4	32K / 19.5 GB	20619	24
...5 Coder 32B Instruct GPTQ Int8	32K / 35.1 GB	771	24
QwQ 32B Preview GPTQ 4bit	32K / 16.1 GB	306	3
Qwen Qwen1.5 32B 4 Bit Gptq	32K / 19.2 GB	8	0
Qwen1.5 32B Chat GPTQ Int8	32K / 34.9 GB	10	1
...Logic Mix 3 32B Mlx OptiQ 5bit	128K / 22.3 GB	41	1
...pSeek R1 Distill Qwen 32B 4bit	128K / 18.5 GB	7795	51
Hydraulic Deepseek 16bit	128K / 65.8 GB	52	0

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-32B-Chat-GPTQ-Int4.