What are the hardware requirements for Qwen1.5 72B Chat GPTQ Int4?

Qwen1.5 72B Chat GPTQ Int4 requires approximately 41.3 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 72B Chat GPTQ Int4 and how large is it?

Qwen1.5 72B Chat GPTQ Int4 is developed by Qwen, a model with 72b 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 72B Chat GPTQ Int4?

Qwen1.5 72B 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 72B Chat GPTQ Int4 by Qwen — VRAM 41.3GB, 32K context

Name: Qwen1.5 72B Chat GPTQ Int4
Author: Qwen

Qwen1.5 72B Chat GPTQ Int4 is an open-source language model by Qwen. Features: 72b LLM, VRAM: 41.3GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.14.

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/Qwen1.5-72B-Chat-GPTQ-Int4

Qwen1.5 72B Chat GPTQ Int4 Parameters and Internals

Model Type

text-generation, chat

Use Cases

Considerations:

If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.

Additional Notes

For the beta version, temporarily did not include GQA and the mixture of SWA and full attention.

Training Details

Data Volume:

large amount of data

Methodology:

pretraining followed by supervised finetuning and direct preference optimization

Context Length:

32768

Model Architecture:

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

LLM Name	Qwen1.5 72B Chat GPTQ Int4
Repository 🤗	https://huggingface.co/Qwen/Qwen1.5-72B-Chat-GPTQ-Int4
Model Size	72b
Required VRAM	41.3 GB
Updated	2026-07-19
Maintainer	Qwen
Model Type	qwen2
Model Files	4.0 GB: 1-of-11 4.0 GB: 2-of-11 3.9 GB: 3-of-11 4.0 GB: 4-of-11 4.0 GB: 5-of-11 4.0 GB: 6-of-11 3.9 GB: 7-of-11 4.0 GB: 8-of-11 4.0 GB: 9-of-11 3.0 GB: 10-of-11 2.5 GB: 11-of-11
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 72B 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 72B Chat GPTQ Int4

Best Alternatives	Context / RAM	Downloads	Likes
Kimi Dev 72B GPTQ 4bit	128K / 45.8 GB	12	2
Qwen1.5 72B Chat GPTQ	32K / 45.4 GB	2	1
Qwen2.5 72B Instruct GPTQ Int4	32K / 41.6 GB	48399	44
Qwen2.5 72B Instruct GPTQ Int8	32K / 77 GB	1893	28
Qwen2 72B Instruct GPTQ Int8	32K / 77 GB	1702	15
Qwen2 72B Instruct GPTQ Int4	32K / 41.6 GB	96	33
Qwen1.5 72B Chat GPTQ Int8	32K / 77 GB	18	7
Kimi Dev 72B 4bit DWQ	128K / 40.9 GB	4465	21
Kimi Dev 72B 8bit	128K / 77.1 GB	361	2
Kimi Dev 72B 5bit	128K / 50.1 GB	368	2

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-72B-Chat-GPTQ-Int4.