LLaVA 1.6 Mistral 7B
LLaVA 1.6 on Mistral 7B base. Apache 2.0 vision-language with strong OCR.
Overview
LLaVA 1.6 on Mistral 7B base. Apache 2.0 vision-language with strong OCR.
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
- Apache 2.0
- Strong OCR
Weaknesses
- Newer LLaVA-OneVision supersedes
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 1.6 Mistral 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 1.6 Mistral 7B?
Can I use LLaVA 1.6 Mistral 7B commercially?
What's the context length of LLaVA 1.6 Mistral 7B?
Does LLaVA 1.6 Mistral 7B support images?
Source: huggingface.co/liuhaotian/llava-v1.6-mistral-7b
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify LLaVA 1.6 Mistral 7B runs on your specific hardware before committing money.