What are the hardware requirements for Aquila2 7B?

Aquila2 7B requires approximately 30.8 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 Aquila2 7B and how large is it?

Aquila2 7B is developed by BAAI, 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 Aquila2 7B?

Aquila2 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Aquila2 7B by BAAI — VRAM 30.8GB, 8K context

Name: Aquila2 7B
Author: BAAI

Aquila2 7B is an open-source language model by BAAI. Features: 7b LLM, VRAM: 30.8GB, Context: 8K, License: other, LLM Explorer Score: 0.09.

Aquila Conversational Custom code Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/BAAI/Aquila2-7B

Aquila2 7B Parameters and Internals

Model Type

base language model, chat model, long-text chat model

Supported Languages

English (fluent), Chinese Simplified (fluent)

Release Notes

Version:

2024.6.6

Notes:

Updated the basic language model Aquila2-7B with a new tokenizer and support for a longer processing length.

LLM Name	Aquila2 7B
Repository 🤗	https://huggingface.co/BAAI/Aquila2-7B
Model Size	7b
Required VRAM	30.8 GB
Updated	2026-08-24
Maintainer	BAAI
Model Type	aquila
Model Files	5.0 GB: 1-of-7 4.9 GB: 2-of-7 4.9 GB: 3-of-7 4.9 GB: 4-of-7 4.9 GB: 5-of-7 3.8 GB: 6-of-7 2.4 GB: 7-of-7
Model Architecture	AquilaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	143973
Torch Data Type	bfloat16

Rank the Aquila2 7B 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 Aquila2 7B

Best Alternatives	Context / RAM	Downloads	Likes
AquilaChat2 7B 16K	16K / 29.2 GB	134	9
AquilaChat2 7B	2K / 29.2 GB	642	18
Aquilachat 7B	2K / 14.5 GB	31	17
Aquila 7B	2K / 14.5 GB	12	11
Tiny Random Aquilachat	0.1K / 0 GB	325	0
Tiny Random Aquila2	0.1K / 0 GB	71	0
Aquila 2 7B Chat AWQ	2K / 5 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than BAAI/Aquila2-7B.