What are the hardware requirements for Aquila VL 2B Llava Qwen?

Aquila VL 2B Llava Qwen requires approximately 4.4 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 Aquila VL 2B Llava Qwen and how large is it?

Aquila VL 2B Llava Qwen is developed by BAAI, a model with 2b 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 Aquila VL 2B Llava Qwen?

Aquila VL 2B Llava Qwen is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Aquila VL 2B Llava Qwen by BAAI — VRAM 4.4GB, 32K context

Name: Aquila VL 2B Llava Qwen
Author: BAAI

Aquila VL 2B Llava Qwen is an open-source language model by BAAI. Features: 2b LLM, VRAM: 4.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.15.

Arxiv:2410.18558 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-1.5b-i... Dataset:baai/infinity-instruct Dataset:baai/infinity-mm Dataset:baai/infinity-preferen... En Endpoints compatible Multimodal Qwen2 Region:us Safetensors Visual-question-answering Zh

Model Card on HF 🤗: https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen

Aquila VL 2B Llava Qwen Parameters and Internals

LLM Name	Aquila VL 2B Llava Qwen
Repository 🤗	https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen
Base Model(s)	Qwen/Qwen2.5-1.5B-Instruct google/siglip-so400m-patch14-384 Qwen/Qwen2.5-1.5B-Instruct google/siglip-so400m-patch14-384
Model Size	2b
Required VRAM	4.4 GB
Updated	2026-10-02
Maintainer	BAAI
Model Type	qwen2
Model Files	4.4 GB
Supported Languages	en zh
Model Architecture	LlavaQwenForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Aquila VL 2B Llava Qwen 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 Aquila VL 2B Llava Qwen

Best Alternatives	Context / RAM	Downloads	Likes
Infinity VL 2B Llava Qwen	32K / GB	12	4