gguf2oom
Convert GGUF models to OomLlama's compact OOM format - 2x smaller
Quick Start
pip install gguf2oom
# Convert any GGUF to OOM Q2
gguf2oom model.gguf model.oom
# Show GGUF file info
gguf2oom --info model.gguf
Why Convert to OOM?
| Format | 32B Model | 70B Model |
|---|---|---|
| GGUF Q4_K | ~20 GB | ~40 GB |
| OOM Q2 | ~10 GB | ~20 GB |
The OOM format uses Q2 quantization (2-bit weights) with per-block scale/min values, achieving ~2x compression vs GGUF Q4.
Usage
# Basic conversion
gguf2oom input.gguf output.oom
# Show model info without converting
gguf2oom --info input.gguf
# Help
gguf2oom --help
How It Works
- Reads GGUF file (any quantization: Q4_K, Q8_0, F16, etc.)
- Dequantizes each tensor to FP32
- Requantizes to OOM Q2 format (2 bits per weight)
- Writes compact .oom file with OOML magic header
Use with OomLlama
# Install both
pip install gguf2oom oomllama
# Convert
gguf2oom humotica-32b.gguf humotica-32b.oom
# Run inference
oomllama generate --model humotica-32b.oom "Hello!"
Platform Support
The converter automatically downloads the right binary for your platform:
- Linux x86_64
- Linux aarch64 (coming soon)
- macOS x86_64 (coming soon)
- macOS arm64 (coming soon)
Binaries are cached in ~/.cache/gguf2oom/
Links
- OomLlama - Run OOM models
- GitHub
- HuggingFace Models
Credits
- Converter: Humotica AI Lab
- OOM Format: Gemini IDD & Root AI
- GGUF Reader: Inspired by llama.cpp
One Love, One fAmIly 🦙
Built by Humotica AI Lab
Metadata
Release files for gguf2oom 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| gguf2oom-0.1.0.tar.gz | 3.1 kB | Without provenance | Details for gguf2oom-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| gguf2oom-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for gguf2oom-0.1.0-py3-none-any.whl |
Total release size: 6.9 kB
Release files / gguf2oom-0.1.0.tar.gz
| Download URL | gguf2oom-0.1.0.tar.gz |
|---|---|
| Size | 3.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
711a9eff9750fb4b02208d3e2456db0c39cc3133dc252154cd70bda87173380b
|
|
BLAKE2b-256 checksum How to use checksums |
68382ea57cc6d5797f685ae32821fce4332a83cb71e80cd5555391b16fbffe31
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / gguf2oom-0.1.0-py3-none-any.whl
| Download URL | gguf2oom-0.1.0-py3-none-any.whl |
|---|---|
| Size | 3.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
64b980dab05f7cd4233e169602fda57bb3d41c0995b0eab2750ee5d1ca53b114
|
|
BLAKE2b-256 checksum How to use checksums |
43902ec2c4a7d288ca03f6afc4c6545941007f5965d241a2c29815657491e3df
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for gguf2oom 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.