What are the hardware requirements for Llama 2 7B AWQ?

Llama 2 7B AWQ requires approximately 3.9 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 7B AWQ and how large is it?

Llama 2 7B AWQ is developed by TheBloke, a model with 7b 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 7B AWQ?

Llama 2 7B AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 2 7B AWQ by TheBloke — VRAM 3.9GB, 4K context

Name: Llama 2 7B AWQ
Author: TheBloke

Llama 2 7B AWQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 3.9GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.1.

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

Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-7B-AWQ

Llama 2 7B AWQ Parameters and Internals

Model Type

llama

Use Cases

Areas:

commercial, research

Primary Use Cases:

assistant-like chat

Training Details

Data Sources:

A new mix of publicly available online data

Data Volume:

2.0T tokens

Methodology:

Pretrained using publicly available online data.

Context Length:

4000

Training Time:

January 2023 - July 2023

Hardware Used:

Meta's Research Super Cluster, A100-80GB GPUs

Model Architecture:

Auto-regressive language model with optimized transformer architecture

Input Output

Input Format:

{prompt}

LLM Name	Llama 2 7B AWQ
Repository 🤗	https://huggingface.co/TheBloke/Llama-2-7B-AWQ
Model Name	Llama 2 7B
Model Creator	Meta
Base Model(s)	Llama 2 7B Hf meta-llama/Llama-2-7b-hf
Model Size	7b
Required VRAM	3.9 GB
Updated	2026-07-22
Maintainer	TheBloke
Model Type	llama
Model Files	3.9 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 7B 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 7B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Smaugv0.1 AWQ	195K / 19.3 GB	9	1
Yarn Llama 2 7B 64K AWQ	64K / 3.9 GB	14	0
Calm2 7B Chat AWQ	32K / 4.4 GB	9	1
Llama 2 7B 32K Instruct AWQ	32K / 3.9 GB	3	2
... SWE Llama 7B Updated 4bit AWQ	16K / 3.9 GB	5	0
Pandalyst 7B V1.2 AWQ	16K / 3.9 GB	6	1
Tora Code 7B V1.0 AWQ	16K / 3.9 GB	5	0
...eechless Tora Code 7B V1.0 AWQ	16K / 3.9 GB	6	1
CodeLlama 7B Instruct AWQ	16K / 3.9 GB	278	4
Pandalyst 7B V1.1 AWQ	16K / 3.9 GB	11	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-7B-AWQ.