LI

sd3.5 lite

LiteGGUF by calcuisUpdated 2025-08-21
Download on Hugging Face
Parameters2.47B
Context—
Layers—
Architecturepig
Smallest quant1.4 GB
Quick answer

sd3.5 lite needs about 2.5 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 23 quants, from 1.4 GB (IQ3_XXS) to 8.8 GB (Q8_0).

sd3.5 lite – a 2.47B parameter diffusion model in GGUF format

sd3.5 lite is a 2.47B parameter diffusion model based on the pig architecture. It is available in multiple quantizations and can be run with gguf-connector or gguf-node. The model supports 8‑step inference for faster generation.

Good at

  • Fast 8‑step inference
  • Compact quantizations
  • Stable image output

Limits

  • No vision support
  • Limited context tokens
  • License type "other"

Best for

  • Low‑VRAM image generation
  • Rapid prototyping
  • ComfyUI integration

Who it’s for. Developers and hobbyists who need a lightweight diffusion model for quick image generation on modest hardware. The model is suitable for integration into pipelines that use gguf-connector or gguf-node.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS1.4 GB 2.1 GB
Fits Get file →
Q3_K_S1.4 GB 2.1 GB
Fits Get file →
IQ3_S1.5 GB 2.1 GB
Fits Get file →
Q3_K_M1.5 GB 2.2 GB
Fits Get file →
IQ4_XS1.7 GB 2.4 GB
Fits Get file →
IQ4_NL1.7 GB 2.5 GB
Fits Get file →
Q4_01.7 GB 2.5 GB
Fits Get file →
Q4_K_S1.7 GB 2.5 GB
Fits Get file →
Q4_K_M1.8 GB 2.5 GB
Fits Get file →
Q4_11.9 GB 2.6 GB
Fits Get file →
Q5_02.0 GB 2.8 GB
Fits Get file →
Q5_K_S2.0 GB 2.8 GB
Fits Get file →
Q5_K_M2.1 GB 2.8 GB
Fits Get file →
Q5_12.2 GB 2.9 GB
Fits Get file →
Q6_K2.3 GB 3.1 GB
Fits Get file →
MXFP4_MOE2.9 GB 3.7 GB
Fits Get file →
Q8_02.9 GB 3.7 GB
Fits Get file →
IQ4_NL4.8 GB 5.8 GB
Fits Get file →
Q4_04.8 GB 5.8 GB
Fits Get file →
Q5_05.8 GB 7.0 GB
Fits Get file →
Q6_K6.4 GB 7.7 GB
Tight Get file →
MXFP4_MOE8.8 GB 10.3 GB
Too big Get file →
Q8_08.8 GB 10.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 1.74 GB, memory 2.5 GB at 8k context). For 16 GB VRAM, Q5_0 or Q5_K_S (file size 2.02 GB, memory 2.8 GB). For 24 GB VRAM, Q6_K (file size 2.32 GB, memory 3.1 GB).

What GPU do you need for sd3.5 lite?

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 MXFP4_MOE (2.9 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_NL (4.8 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is MXFP4_MOE (8.8 GB file, about 10.3 GB in use).

Which sd3.5 lite quant should you choose?

Q4_K_M is the usual starting point for sd3.5 lite: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 2.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ3_XXS at 1.4 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

Architecturepig
Parameters2.47B

Source

Quantized bycalcuis
FamilyLite
Licenseother
Downloads (HF)1,398
Last updated2025-08-21

Frequently asked questions about sd3.5 lite

How much VRAM does sd3.5 lite need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.8 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 sd3.5 lite on an 8 GB GPU?

Yes, with Q6_K: the 6.4 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sd3.5 lite GGUF?

It depends on the quant: IQ3_XXS is 1.4 GB, Q3_K_S is 1.4 GB, IQ3_S is 1.5 GB, Q3_K_M is 1.5 GB, IQ4_XS is 1.7 GB, IQ4_NL is 1.7 GB and 17 more.

Where can I download sd3.5 lite GGUF?

The files are on Hugging Face in the calcuis/sd3.5-lite-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does sd3.5 lite use?

Hugging Face lists the license as other. 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 sd3.5 lite on 8 GB VRAM?

Yes, use Q4_0 or Q4_K_S quantizations; they require about 2.5 GB of VRAM at 8k context.

Does sd3.5 lite support text‑to‑image only?

Yes, the model is a diffusion model and does not include vision capabilities.

What is the fastest inference mode?

The 8‑step mode is faster, roughly 70% faster than the original 24‑step, while maintaining similar quality.

Similar models

Browse all →

More from calcuis

All by calcuis →

More Lite models

All Lite →

Other tiny models

All tiny models →