convert-hf-to-gguf
Convert Hugging Face transformer models to the GGUF format for use with llama.cpp and compatible inference engines.
Installation
pip install convert-hf-to-gguf
Usage
Convert a Hugging Face model directory to GGUF:
convert-hf-to-gguf /path/to/model-directory
Specify the output format (default: auto):
convert-hf-to-gguf --outtype f16 /path/to/model-directory
Download and convert a model directly from Hugging Face Hub:
convert-hf-to-gguf --remote --outtype q8_0 HuggingFaceTB/SmolLM2-1.7B-Instruct
Options
| Option | Description |
|---|---|
--outtype |
Output format: f32, f16, bf16, q8_0, tq1_0, tq2_0, auto (default) |
--vocab-only |
Extract only the vocabulary |
--outfile |
Output file path |
--remote |
Read model files remotely from Hugging Face Hub |
--mmproj |
Export multimodal projector for vision models |
--print-supported-models |
List all supported model architectures |
--verbose |
Increase output verbosity |
--split-max-size |
Split output into chunks of max size (e.g., 4G) |
See --help for the full list of options.
Supported models
Convert-hf-to-gguf supports a wide range of model architectures including: LLaMA, Mistral, Mixtral, Qwen, DeepSeek, Falcon, Gemma, Phi, BERT, Mamba, GPT-NeoX, StableLM, Command-R, DBRX, OLMo, Grok, and many more.
Run convert-hf-to-gguf --print-supported-models for the full list.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for convert-hf-to-gguf 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| convert_hf_to_gguf-0.1.1.tar.gz | 292.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| convert_hf_to_gguf-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 657.2 kB
Release files / convert_hf_to_gguf-0.1.1.tar.gz
| Download URL | convert_hf_to_gguf-0.1.1.tar.gz |
|---|---|
| Size | 292.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f1c0f299726057d0fe95f69c728edf1bc156a40544fe073b297195ce80665735
|
|
BLAKE2b-256 checksum How to use checksums |
e8a3124660877fadd0766693e37c9217f5b0e41e804d296975deb9d1df87858b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.3.4 CPython/3.14.6 Linux/7.1.3+deb14-amd64
|
Release files / convert_hf_to_gguf-0.1.1-py3-none-any.whl
| Download URL | convert_hf_to_gguf-0.1.1-py3-none-any.whl |
|---|---|
| Size | 365.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
271820588f890a7d639723784c168495847b6d4830d307384c475db53ceb02b4
|
|
BLAKE2b-256 checksum How to use checksums |
fb160def4f1e999c13505f122ed65fe7cdd685ed605ef4b2d5a28f73494e6e65
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.3.4 CPython/3.14.6 Linux/7.1.3+deb14-amd64
|
