gguf2oom 0.1.0

Convert GGUF models to OomLlama's compact OOM format - 2x smaller

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

1. Reads GGUF file (any quantization: Q4_K, Q8_0, F16, etc.)
2. Dequantizes each tensor to FP32
3. Requantizes to OOM Q2 format (2 bits per weight)
4. 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