pixart needs about 1.6 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 1.0 GB (Q3_K_M) to 2.9 GB (Q4_0).
Pixart-α: 0.611B parameter text‑to‑image diffusion model
Pixart-α is a 0.611B parameter diffusion‑transformer that generates 1024px images from text prompts in a single sampling process. It uses a fixed T5 text encoder and a VAE latent encoder. The model is released under CreativeML Open RAIL++-M license.
Good at
- Fast single‑pass image generation
- High‑resolution 1024×1024 output
- Text‑driven image editing
Limits
- Requires 1.6–1.9 GB VRAM for Q4_K_M to F16 quants
- No vision or audio support
- License restricts commercial use without permission
Best for
- Creating detailed artwork from prompts
- Rapid prototyping of image generation pipelines
- Integrating into ComfyUI workflows
Who it’s for. Developers and researchers needing a lightweight, high‑resolution text‑to‑image model. Suitable for local inference on GPUs with 8 GB VRAM or more. Ideal for artists and designers exploring diffusion techniques.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 1.7 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q4_0 | 2.9 GB | 3.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1 GB file, ~1.6 GB memory). If more memory is available, F16 (1.22 GB file, ~1.9 GB memory) offers higher precision. Avoid Q4_0 (2.9 GB file) unless you have 4 GB+ VRAM.
What GPU do you need for pixart?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_0 (2.9 GB file, about 3.7 GB in use).
Which pixart quant should you choose?
Q4_K_M is the usual starting point for pixart: it balances file size and quality well. Here it is a 1.0 GB file.
If memory is tight, the smallest file is Q3_K_M at 1.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about pixart
How much VRAM does pixart need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 1.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run pixart on an 8 GB GPU?
Yes, with Q4_0: the 2.9 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of pixart GGUF?
It depends on the quant: Q3_K_M is 1.0 GB, Q3_K_M is 1.0 GB, Q3_K_M is 1.0 GB, Q3_K_M is 1.0 GB, Q4_K_M is 1.0 GB, Q4_K_M is 1.0 GB and 15 more.
Where can I download pixart GGUF?
The files are on Hugging Face in the calcuis/pixart repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does pixart use?
Hugging Face lists the license as openrail++. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Pixart-α on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 1.6 GB VRAM, which fits within an 8 GB budget.
Does Pixart-α support image editing?
Yes, it can modify images based on text prompts using its latent diffusion architecture.