Instructions to use mozilla-ai/llava-v1.5-7b-llamafile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mozilla-ai/llava-v1.5-7b-llamafile with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mozilla-ai/llava-v1.5-7b-llamafile",
	filename="llava-v1.5-7b-Q4_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mozilla-ai/llava-v1.5-7b-llamafile with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
llama-cli -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
llama-cli -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Use Docker

docker model run hf.co/mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

LM Studio
Jan
Ollama
How to use mozilla-ai/llava-v1.5-7b-llamafile with Ollama:
```
ollama run hf.co/mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
```

Unsloth Studio new

How to use mozilla-ai/llava-v1.5-7b-llamafile with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mozilla-ai/llava-v1.5-7b-llamafile to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mozilla-ai/llava-v1.5-7b-llamafile to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mozilla-ai/llava-v1.5-7b-llamafile to start chatting

Docker Model Runner
How to use mozilla-ai/llava-v1.5-7b-llamafile with Docker Model Runner:
```
docker model run hf.co/mozilla-ai/llava-v1.5-7b-llamafile:Q8_0
```

Lemonade

How to use mozilla-ai/llava-v1.5-7b-llamafile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mozilla-ai/llava-v1.5-7b-llamafile:Q8_0

Run and chat with the model

lemonade run user.llava-v1.5-7b-llamafile-Q8_0

List all available models

lemonade list

Software Last Updated: 2025-03-31

Llamafile Version: 0.9.2

LLaVA Model Card

Model details

Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

Model date: LLaVA-v1.5-7B was trained in September 2023.

Paper or resources for more information: https://llava-vl.github.io/

License

Where to send questions or comments about the model: https://github.com/haotian-liu/LLaVA/issues

Intended use

Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
158K GPT-generated multimodal instruction-following data.
450K academic-task-oriented VQA data mixture.
40K ShareGPT data.

Evaluation dataset

A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.

Downloads last month: 8,119

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support