LLaVA-OneVision 7B

Overview

An Apache-licensed 7B vision-language model from LMMs-Lab, combining SigLIP SO400M with Qwen2-7B. Handles single images, multi-image inputs, and video at over 170k monthly downloads.

When to pick this model

• Self-hosted VLM apps needing a permissive license
• Multi-image reasoning and short video understanding
• Fine-tuning base for domain-specific vision tasks
• Cost-sensitive image captioning and VQA pipelines

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	5 GB
Q5_K_M	6 GB
Q8_0	9 GB
FP16 (no quantization)	16 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• Fully Apache 2.0 with no commercial gotchas
• Genuine multi-image and video support
• Mature ecosystem with strong community traction
• Solid Qwen2-7B language backbone

Limitations

• No official Ollama packaging
• English-first; weaker on non-English vision QA
• Outpaced by Qwen3-VL on most 2025 benchmarks

Architecture & training

Architecture: VLM 7B · SO400M + Qwen2-7B · image/multi-image/video

Training: LMMs-Lab (Singapore).

Quick start

# HuggingFace : lmms-lab/llava-onevision-qwen2-7b-ov

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.