What are the hardware requirements for Llama 2 13B Chat AWQ?

Llama 2 13B Chat AWQ requires approximately 7.2 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 2 13B Chat AWQ and how large is it?

Llama 2 13B Chat AWQ is developed by TheBloke, a model with 13b 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 Llama 2 13B Chat AWQ?

Llama 2 13B Chat AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 2 13B Chat AWQ by TheBloke — VRAM 7.2GB, 4K context

Name: Llama 2 13B Chat AWQ
Author: TheBloke

Llama 2 13B Chat AWQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.2GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.09.

Arxiv:2307.09288 4-bit Awq Base model:meta-llama/llama-2-... Base model:quantized:meta-llam... Deploy:azure En Facebook Llama Llama2 Meta Pytorch Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ

Llama 2 13B Chat AWQ Parameters and Internals

Model Type

llama

Use Cases

Areas:

commercial, research

Applications:

dialogue, natural language generation

Primary Use Cases:

assistant-like chat, natural language generation tasks

Limitations:

use only in English, avoid inappropriate legal applications

Considerations:

Use proper formatting for optimal feature extraction and performance.

Additional Notes

AWQ models support efficient inference and faster execution. Compatible with vLLM and AutoAWQ.

Training Details

Data Sources:

publicly available online data

Data Volume:

2.0T tokens

Methodology:

auto-regressive language model with transformer architecture, supervised fine-tuning (SFT), and reinforcement learning with human feedback (RLHF)

Context Length:

4096

Hardware Used:

A100-80GB GPUs (TDP of 350-400W)

Model Architecture:

Transformer

Safety Evaluation

Methodologies:

truthfulQA, Toxigen benchmarks

Findings:

Llama-2-Chat models demonstrate high-performance in safety tests

Risk Categories:

misinformation, bias

Ethical Considerations:

Testing conducted to date has been in English and may not cover all scenarios. Potential for inaccurate or objectionable responses exists.

Responsible Ai Considerations

Fairness:

Testing conducted to date has been in English. Model may exhibit bias.

Transparency:

Limited model transparency as it is fine-tuned and pretrained with human feedback.

Accountability:

Meta is accountable for the model's performance and outputs.

Mitigation Strategies:

Developers advised to perform safety testing and tuning tailored to applications.

Input Output

Input Format:

Structured text with prompt template

Accepted Modalities:

text

Output Format:

Generated text

Performance Tips:

Use 'INST' for better performance in chat tasks.

LLM Name	Llama 2 13B Chat AWQ
Repository 🤗	https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ
Model Name	Llama 2 13B Chat
Model Creator	Meta Llama 2
Base Model(s)	Llama 2 13B Chat Hf meta-llama/Llama-2-13b-chat-hf
Model Size	13b
Required VRAM	7.2 GB
Updated	2026-07-15
Maintainer	TheBloke
Model Type	llama
Model Files	7.2 GB
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Llama 2 13B Chat AWQ 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 Llama 2 13B Chat AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Yarn Llama 2 13B 128K AWQ	128K / 7.2 GB	4	2
LongAlign 13B 64K AWQ	64K / 7.2 GB	4	2
...oboros L2 13B 2 1 YaRN 64K AWQ	64K / 7.2 GB	5	2
OrcaMaid V3 13B 32K AWQ	32K / 7.2 GB	5	4
OrcaMaid V2 FIX 13B 32K AWQ	32K / 7.2 GB	7	1
NexusRaven V2 13B AWQ	16K / 7.2 GB	11	3
NexusRaven V2 13B AWQ	16K / 7.2 GB	1	3
...th CodeLlama 13B Python Hf AWQ	16K / 7.5 GB	6	0
WhiteRabbitNeo 13B AWQ	16K / 7.2 GB	332	4
NexusRaven V2 13B AWQ	16K / 7.2 GB	10	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-13B-chat-AWQ.