What are the hardware requirements for Qwen 14B Chat Int8?

Qwen 14B Chat Int8 requires approximately 15.9 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen 14B Chat Int8 and how large is it?

Qwen 14B Chat Int8 is developed by Qwen, a model with 14b 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 Qwen 14B Chat Int8?

Qwen 14B Chat Int8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen 14B Chat Int8 by Qwen — VRAM 15.9GB, 8K context

Name: Qwen 14B Chat Int8
Author: Qwen

Qwen 14B Chat Int8 is an open-source language model by Qwen. Features: 14b LLM, VRAM: 15.9GB, Context: 8K, LLM Explorer Score: 0.09.

Arxiv:2009.03300 Arxiv:2210.03629 Arxiv:2305.05280 Arxiv:2305.08322 Arxiv:2309.16609 8-bit Custom code En Gptq Qwen Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen-14B-Chat-Int8

Qwen 14B Chat Int8 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Research, Commercial applications

Supported Languages

Chinese (full), English (limited), Multilingual (limited)

Training Details

Data Sources:

web text, books, code

Data Volume:

large scale

Methodology:

alignment techniques

Context Length:

2048

Hardware Used:

single A100-SXM4-80G GPU

Model Architecture:

Transformer-based, RoPE relative position encoding, SwiGLU for activation function, RMSNorm normalization

Input Output

Input Format:

tiktoken-based tokenization

Accepted Modalities:

text

Output Format:

text-based

Performance Tips:

Optional installation of flash-attention for acceleration

Release Notes

Version:

Qwen-14B-Chat-Int8

Notes:

Int8 quantized version release with minor performance loss compared to full precision models.

LLM Name	Qwen 14B Chat Int8
Repository 🤗	https://huggingface.co/Qwen/Qwen-14B-Chat-Int8
Model Size	14b
Required VRAM	15.9 GB
Updated	2026-08-05
Maintainer	Qwen
Model Type	qwen
Model Files	2.0 GB: 1-of-8 2.0 GB: 2-of-8 2.0 GB: 3-of-8 2.0 GB: 4-of-8 2.0 GB: 5-of-8 2.0 GB: 6-of-8 2.0 GB: 7-of-8 1.9 GB: 8-of-8
Supported Languages	zh en
Model Architecture	QWenLMHeadModel
Context Length	8192
Model Max Length	8192
Transformers Version	4.32.0
Tokenizer Class	QWenTokenizer
Vocabulary Size	152064

Rank the Qwen 14B Chat Int8 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 Qwen 14B Chat Int8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen 14B Chat	8K / 28.4 GB	3837	373
Qwen 14B	8K / 28.4 GB	1997	214
Qwen 14B Chat Int4	8K / 9.6 GB	642	100

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen-14B-Chat-Int8.