SD

SDXL Lightning Quantized

SdxlGGUF by TensorVizionUpdated 2026-09-06
Download on Hugging Face
Parameters2.57B
Context—
Layers—
Architecturesdxl
Smallest quant1.0 GB
Quick answer

SDXL Lightning Quantized needs about 2.3 GB of memory at Q4_K (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.0 GB (Q2_K) to 2.7 GB (Q8_0).

SDXL Lightning Quantized – fast, low‑VRAM image generation

SDXL Lightning Quantized offers a lightweight GGUF format for SDXL image generation. It provides three quantization levels, balancing speed, VRAM usage, and image quality. The model is suitable for GPUs with limited memory.

Good at

  • Low‑VRAM inference
  • Fast generation
  • High image fidelity at Q8_0

Limits

  • No vision support beyond SDXL
  • Requires 8k context for estimates
  • License restricts commercial use

Best for

  • Rapid prototyping on 4–6 GB GPUs
  • Batch image generation on RTX 4060
  • Low‑resource deployment

Who it’s for. Developers and artists needing quick SDXL inference on modest GPUs. It is ideal for those who prioritize speed and memory efficiency over absolute fidelity.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.6 GB
Fits Get file →
Q4_K1.6 GB 2.3 GB
Fits Get file →
Q8_02.7 GB 3.6 GB
Fits Get file →

For 4–6 GB VRAM, use Q2_K (1 GB file, ~1.6 GB memory) or Q4_K (1.57 GB file, ~2.3 GB memory). If you have 8 GB or more, Q4_K is recommended for a good balance, or Q8_0 (2.73 GB file, ~3.6 GB memory) for near‑FP16 quality.

What GPU do you need for SDXL Lightning Quantized?

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 Q8_0 (2.7 GB file, about 3.6 GB in use).

Which SDXL Lightning Quantized quant should you choose?

Q4_K (1.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 1.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturesdxl
Parameters2.57B

Source

Quantized byTensorVizion
FamilySdxl
Downloads (HF)284
Last updated2026-09-06

Frequently asked questions about SDXL Lightning Quantized

How much VRAM does SDXL Lightning Quantized need?

About 2.3 GB at Q4_K with an 8K context window. That is the 1.6 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 SDXL Lightning Quantized on an 8 GB GPU?

Yes, with Q8_0: the 2.7 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SDXL Lightning Quantized GGUF?

It depends on the quant: Q2_K is 1.0 GB, Q4_K is 1.6 GB, Q8_0 is 2.7 GB.

Where can I download SDXL Lightning Quantized GGUF?

The files are on Hugging Face in the TensorVizion/SDXL-Lightning-Quantized repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SDXL Lightning Quantized use?

Hugging Face lists the license as creativeml-openrail-m. 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 Q4_K on an 8 GB GPU?

Yes, Q4_K uses about 2.3 GB at 8k context, leaving room for other processes.

Is the model suitable for 4 GB VRAM?

Q2_K is the only variant that comfortably fits 4–6 GB VRAM, using about 1.6 GB at 8k context.

What license does the model use?

It is released under the CreativeML OpenRAIL-M license, with downstream restrictions from the original SDXL license.

Similar models

Browse all →

More from TensorVizion

All by TensorVizion →

More Sdxl models

All Sdxl →

Other tiny models

All tiny models →