Skip to main content
Local LLM Guide

Model

LLaVA 1.6 Vicuna 7B

Start with a supported compressed build and short context. 16GB RAM estimate. Best use: Local image captioning and visual question-answering demos

7BVision language

Best use

Local image captioning and visual question-answering demos · Small multimodal chat workflows

Memory planning

16GB RAM estimate

Expected pace

Depends on your hardware, app, and conversation length

License

Llama 2 Community License; read the model’s terms before use

Who should use this model?

  • Local image captioning and visual question-answering demos
  • Small multimodal chat workflows
  • Research or hobbyist use on commodity hardware
  • Testing LLaVA-compatible local runtimes

Choose something else when

  • You need production-grade OCR or document intelligence
  • You need a current commercial-friendly permissive license stack
  • You need structured tool calling
  • You need long-context text-only chat

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. For chat models, context includes the instructions, conversation, and answer. Longer context needs more memory.

CPU only
Memory or response time may limit use. Try a smaller model first.
8GB system memory
Memory or response time may limit use. Try a smaller model first.
16GB system memory
A possible starting point with a compressed model and short conversation; check the exact file size.
32GB system memory
A possible starting point with a compressed model and short conversation; check the exact file size.
8GB GPU memory
A possible starting point with a compressed model and short conversation; check the exact file size.
12GB GPU memory
A possible starting point with a compressed model and short conversation; check the exact file size.
24GB GPU memory
A possible starting point with a compressed model and short conversation; check the exact file size.
Apple unified memory
A possible starting point with a compressed model and short conversation; check the exact file size.

Model facts that change the decision

Parameters
7B
Input
Text · Image
Published context limit
4,096 tokens
Model format
Hugging Face Transformers · GGUF · Ollama
Suggested compression
Q4_K_M for broad local image-chat use; Q5_K_M when memory allows.
Typical Q4 file
4.08GB before runtime and context overhead
Languages
English

Using image input

This model needs an app or library that supports its image-processing components. Follow the exact model’s instructions for preparing image inputs. Some GGUF downloads also need a matching projector file; loading the text model alone does not establish image support.

First setup

Ollama

ollama run llava:7b-v1.6-vicuna-q4_K_M

LM Studio: Use a LLaVA-capable GGUF workflow and ensure that the matching multimodal projector is selected if the interface asks for one.

llama.cpp

Use a current llama.cpp LLaVA/multimodal binary and pass the matching --mmproj projector file when using raw GGUF files.

Conditions that change the answer

  • Community GGUF conversion is not an official LLaVA artifact.
  • Local vision inference may require a separate projector/mmproj file depending on runtime.
  • RAM and VRAM estimates are derived from GGUF/Ollama package size plus conservative overhead; conversation memory, image resolution, batch size, GPU offload and runtime support can materially change memory needs.

Read the controlling license text →