What are the hardware requirements for LLaVA Video 7B Qwen2?

LLaVA Video 7B Qwen2 requires approximately 16.1 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 LLaVA Video 7B Qwen2 and how large is it?

LLaVA Video 7B Qwen2 is developed by lmms-lab, 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 LLaVA Video 7B Qwen2?

LLaVA Video 7B Qwen2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LLaVA Video 7B Qwen2 by lmms-lab — VRAM 16.1GB, 32K context

Name: LLaVA Video 7B Qwen2
Author: lmms-lab

LLaVA Video 7B Qwen2 is an open-source language model by lmms-lab. Features: 7b LLM, VRAM: 16.1GB, Context: 32K, License: apache-2.0, Instruction-Based.

Arxiv:2410.02713 Base model:finetune:lmms-lab/l... Base model:lmms-lab/llava-onev... Dataset:lmms-lab/llava-onevisi... Dataset:lmms-lab/llava-video-1... En Endpoints compatible Instruct Llava Model-index Multimodal Region:us Safetensors Sharded Tensorflow Video-text-to-text

Model Card on HF 🤗: https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2

LLaVA Video 7B Qwen2 Parameters and Internals

LLM Name	LLaVA Video 7B Qwen2
Repository 🤗	https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2
Base Model(s)	Llava Onevision Qwen2 7B Si lmms-lab/llava-onevision-qwen2-7b-si
Model Size	7b
Required VRAM	16.1 GB
Updated	2026-08-09
Maintainer	lmms-lab
Model Type	llava
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 1.3 GB: 4-of-4 0.0 GB
Supported Languages	en
Model Architecture	LlavaQwenForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the LLaVA Video 7B Qwen2 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 LLaVA Video 7B Qwen2

Best Alternatives	Context / RAM	Downloads	Likes
LongVA 7B	218K / 15.9 GB	865	15
Pangea 7B	32K / 15.9 GB	3215	133
Llava Onevision Qwen2 7B Si	32K / 16.1 GB	140	12

Note: green Score (e.g. "73.2") means that the model is better than lmms-lab/LLaVA-Video-7B-Qwen2.