LLaVA-OneVision 7B
LLaVA-OneVision unified single-image / multi-image / video VLM on Qwen 2 base.
Overview
LLaVA-OneVision unified single-image / multi-image / video VLM on Qwen 2 base.
Family & lineage
How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.
Strengths
- Single-image + video support
- Apache 2.0
Weaknesses
- Qwen 2.5-VL 7B is sharper for most tasks
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 4.5 GB | 7 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of LLaVA-OneVision 7B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run LLaVA-OneVision 7B?
Can I use LLaVA-OneVision 7B commercially?
What's the context length of LLaVA-OneVision 7B?
Does LLaVA-OneVision 7B support images?
Source: huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify LLaVA-OneVision 7B runs on your specific hardware before committing money.