What are the hardware requirements for Openvla 7B?

Openvla 7B requires approximately 15.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Openvla 7B and how large is it?

Openvla 7B is developed by openvla, 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 Openvla 7B?

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

Openvla 7B by openvla — VRAM 15.2GB

Name: Openvla 7B
Author: openvla

Openvla 7B is an open-source language model by openvla. Features: 7b LLM, VRAM: 15.2GB, License: mit, LLM Explorer Score: 0.2.

Arxiv:2406.09246 Custom code En Feature-extraction Image-text-to-text Multimodal Openvla Region:us Robotics Safetensors Sharded Tensorflow Vla

Model Card on HF 🤗: https://huggingface.co/openvla/openvla-7b

Openvla 7B Parameters and Internals

LLM Name	Openvla 7B
Repository 🤗	https://huggingface.co/openvla/openvla-7b
Model Size	7b
Required VRAM	15.2 GB
Updated	2026-08-10
Maintainer	openvla
Model Type	openvla
Model Files	7.0 GB: 1-of-3 7.0 GB: 2-of-3 1.2 GB: 3-of-3
Supported Languages	en
Model Architecture	OpenVLAForActionPrediction
License	mit
Model Max Length	2048
Transformers Version	4.40.1
Tokenizer Class	LlamaTokenizer
Padding Token	<PAD>
Torch Data Type	bfloat16

Rank the Openvla 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