---
license: other
license_name: ltx-2-community-license
tags:
- hlwq
- video-generation
- audio-video
- ltx-video
- bit-packed
base_model: Lightricks/LTX-2.3
pipeline_tag: image-to-video
arxiv: '2603.29078'
---

> [!IMPORTANT]
> **Naming notice (2026-04-10).** The "HLWQ" technique used in this model is being rebranded to **HLWQ (Hadamard-Lloyd Weight Quantization)**. The change is only the name; the algorithm and the weights in this repository are unchanged.
>
> The rebrand resolves a name collision with an unrelated, earlier KV cache quantization method also named HLWQ ([Han et al., arXiv:2502.02617, 2025](https://arxiv.org/abs/2502.02617)). HLWQ addresses **weight** quantization with a **deterministic Walsh-Hadamard rotation** and Lloyd-Max scalar codebook; Han et al.'s HLWQ addresses **KV cache** quantization with a **random polar rotation**. The two methods are technically distinct.
>
> Existing loaders that load this repository by ID continue to work without changes. Future model uploads will use the HLWQ name.
>
> Reference paper for this technique: [arXiv:2603.29078](https://arxiv.org/abs/2603.29078) (v2 in preparation; v1 still uses the old name).

# LTX-2.3 (22B) — HLWQ Q5 (Bit-Packed)

**PQ5 quantized** LTX-2.3 — joint audio-video generation, 22B params.

**46 GB → 15 GB (-68%)** | cos_sim **0.9986** | 1,347 layers quantized

## Download Size

![Download](https://huggingface.co/caiovicentino1/LTX-2.3-22B-HLWQ-Q5/resolve/main/assets/chart_download.png)

## Compression

![Compression](https://huggingface.co/caiovicentino1/LTX-2.3-22B-HLWQ-Q5/resolve/main/assets/chart_compression.png)

| Component | Original | PQ5 Packed | Reduction |
|---|---|---|---|
| **Transformer (1,347 layers)** | 37 GB | 4.6 GB | -88% |
| **VAE + Skip (4,600 layers)** | 9.1 GB | 9.1 GB | BF16 kept |
| **Upscalers** | 1.3 GB | 1.3 GB | BF16 kept |
| **Total** | **46.2 GB** | **15 GB** | **-68%** |

## Quick Start

```bash
# 1. Install
pip install safetensors huggingface_hub scipy

# 2. Download & setup (15 GB)
git clone https://huggingface.co/caiovicentino1/LTX-2.3-22B-HLWQ-Q5 ./LTX-PQ5
cd LTX-PQ5 && python setup.py

# 3. Generate video
python generate_ltx.py --prompt "A cat playing piano in a jazz club"
```

## Architecture

- **22B parameters** — largest video model we've quantized
- 48 transformer blocks, hidden=4096, MLP=16384
- **Joint audio-video generation** — synchronized audio + video
- head_dim=64 (Hadamard-compatible)
- 5,947 tensors total (BF16)
- Spatial + temporal upscalers included

## Files

```
LTX-2.3-22B-HLWQ-Q5/
├── setup.py                          # One-command setup
├── generate_ltx.py                   # Easy generation wrapper
├── polarquant/
│   ├── codes/
│   │   ├── chunk_00_codes.safetensors (1.5 GB)
│   │   ├── chunk_01_codes.safetensors (1.5 GB)
│   │   ├── chunk_02_codes.safetensors (1.5 GB)
│   │   └── chunk_03_codes.safetensors (0.1 GB)
│   └── bf16/
│       └── ltx23_bf16.safetensors    (9.1 GB)
└── upscalers/
    ├── ltx-2.3-spatial-upscaler-x2-1.1.safetensors  (1.0 GB)
    └── ltx-2.3-temporal-upscaler-x2-1.0.safetensors (0.3 GB)
```

## Hardware

| GPU | VRAM | Status |
|-----|------|--------|
| A100 (40 GB) | 40 GB | Recommended |
| A100 (80 GB) | 80 GB | Full speed |
| RTX 4090 (24 GB) | 24 GB | With offloading |

## Links

- [HLWQ Paper](https://arxiv.org/abs/2603.29078)
- [GitHub (HLWQ)](https://github.com/caiovicentino/polarengine-vllm)
- [Original LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3)
- [LTX-2 Paper](https://arxiv.org/abs/2601.03233)
- [LTX GitHub](https://github.com/Lightricks/LTX-2)

## Citation

```bibtex
@article{polarquant2026,
  title={HLWQ: Hadamard-Rotated Lloyd-Max Quantization},
  author={Vicentino, Caio},
  journal={arXiv preprint arXiv:2603.29078},
  year={2026}
}
```

---
*46 GB → 15 GB with cos_sim 0.9986. Quantized with [HLWQ](https://github.com/caiovicentino/polarengine-vllm).*