model-explorer-gguf 1.0.0.post1.dev0

Unofficial GGUF adapter extension for Google Model Explorer - visualize llama.cpp GGUF format models

GGUF Adapter for Model Explorer

Unofficial third-party extension. This project is not affiliated with or endorsed by the llama.cpp project, Georgi Gerganov, or Google. GGUF is the file format of the llama.cpp project.

Visualize GGUF format models in Google Model Explorer.

Installation

pip install model-explorer-gguf

This automatically installs ai-edge-model-explorer as a dependency.

Usage

Command Line

ggufvis path/to/model.gguf

Or directly via model-explorer:

model-explorer --extensions=model_explorer_gguf path/to/model.gguf

Python API

from model_explorer_gguf import GGUFAdapter

adapter = GGUFAdapter()
graph = adapter.convert("path/to/model.gguf")
# graph is a model_explorer Graph — render with model-explorer or inspect programmatically

Features

• Full GGUF v1/v2/v3 spec support
• Hierarchical tensor layout (embeddings, transformer blocks, output)
• Rich metadata display (architecture, context length, layer count, quantization, etc.)
• All quantization types recognized (F32, F16, Q4_0, Q8_0, K-quants, I-quants, etc.)
• Works with any GGUF model (Llama, Mistral, Falcon, Gemma, Phi, etc.)

Supported Formats

Feature	Status
GGUF v1, v2, v3	✓
All metadata types (scalars, strings, arrays)	✓
Tensor information (names, shapes, types, offsets)	✓
Hierarchical graph layout	✓
Multi-shard / split models	✓

Development

git clone https://github.com/johnjg75dev/model-explorer-gguf.git
cd model-explorer-gguf
python -m venv .venv
.venv\Scripts\activate
pip install -e ".[dev]"

Run tests with:

pytest

Report issues at https://github.com/johnjg75dev/model-explorer-gguf/issues

License

Apache 2.0 — see LICENSE.

Trademarks

GGUF and llama.cpp are trademarks of the llama.cpp project. This project is not endorsed by or affiliated with the llama.cpp project or its maintainers.

References

• GGUF Specification
• llama.cpp
• Model Explorer