LU

lumina

LuminaGGUF by calcuisUpdated 2025-09-03
Download on Hugging Face
Parameters2.61B
Context—
Layers—
Architecturelumina
Smallest quant0.2 GB
Quick answer

lumina needs about 2.1 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 0.2 GB (F16) to 3.1 GB (Q8_0).

Lumina: 2.61B parameter image generation model in GGUF format

Lumina is a 2.61B parameter flow‑based diffusion transformer. It is available as a GGUF quantized model and can generate images from text descriptions. The model is licensed under apache-2.0.

Good at

  • Text‑to‑image generation
  • Efficient inference with low‑precision quants
  • Runs on consumer GPUs

Limits

  • No vision support in the base model
  • Requires a text encoder and VAE for full pipeline
  • Limited to 8k context tokens

Best for

  • Creating quick image drafts
  • Testing diffusion models on modest hardware
  • Educational demos of image generation

Who it’s for. Developers and researchers who need a lightweight image generation model for experimentation. The model is suitable for those who prefer open‑source solutions and can integrate it with text encoders and VAE components.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.2 GB 0.7 GB
Fits Get file →
Q2_K_S1.0 GB 1.7 GB
Fits Get file →
Q2_K1.1 GB 1.7 GB
Fits Get file →
Q3_K_M1.1 GB 1.8 GB
Fits Get file →
Q4_K_S1.2 GB 1.9 GB
Fits Get file →
IQ3_XXS1.3 GB 2.0 GB
Fits Get file →
Q4_01.5 GB 2.1 GB
Fits Get file →
Q4_K_M1.5 GB 2.1 GB
Fits Get file →
Q4_01.6 GB 2.3 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
IQ3_S1.6 GB 2.3 GB
Fits Get file →
Q3_K_M1.7 GB 2.4 GB
Fits Get file →
Q5_K_S1.7 GB 2.4 GB
Fits Get file →
Q5_01.8 GB 2.5 GB
Fits Get file →
Q5_K_M1.8 GB 2.5 GB
Fits Get file →
IQ4_XS1.9 GB 2.6 GB
Fits Get file →
Q5_12.0 GB 2.7 GB
Fits Get file →
IQ4_NL2.0 GB 2.7 GB
Fits Get file →
Q4_02.0 GB 2.7 GB
Fits Get file →
Q4_K_M2.0 GB 2.7 GB
Fits Get file →
Q4_12.1 GB 2.9 GB
Fits Get file →
Q6_K2.1 GB 2.9 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.4 GB
Fits Get file →
Q8_02.8 GB 3.6 GB
Fits Get file →
Q8_03.1 GB 4.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_M (est. 2.1 GB memory at 8k context). For 4 GB VRAM, Q2_K_S or Q2_K (est. 1.7 GB). For 2 GB VRAM, Q2_K_S (est. 1.7 GB) is the smallest viable option.

What GPU do you need for lumina?

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 (3.1 GB file, about 4.0 GB in use).

Which lumina quant should you choose?

Q4_K_M is the usual starting point for lumina: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.8 GB, about 1.9 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 F16 at 0.2 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelumina
Parameters2.61B

Source

Quantized bycalcuis
FamilyLumina
Licenseapache-2.0
Downloads (HF)4,937
Last updated2025-09-03

Frequently asked questions about lumina

How much VRAM does lumina need?

About 2.1 GB at Q4_K_M with an 8K context window. That is the 1.5 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 lumina on an 8 GB GPU?

Yes, with Q8_0: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of lumina GGUF?

It depends on the quant: F16 is 0.2 GB, Q2_K_S is 1.0 GB, Q2_K is 1.1 GB, Q3_K_M is 1.1 GB, Q4_K_S is 1.2 GB, IQ3_XXS is 1.3 GB and 20 more.

Where can I download lumina GGUF?

The files are on Hugging Face in the calcuis/lumina-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 lumina use?

Hugging Face lists the license as apache-2.0. 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 Lumina on 8 GB VRAM?

Yes, use the Q4_0 or Q4_K_M quant which requires about 2.1 GB of VRAM at 8k context.

Does Lumina support vision tasks?

No, the base model does not include vision capabilities; it requires a separate text encoder and VAE for image generation.

Similar models

Browse all →

More from calcuis

All by calcuis →

Other tiny models

All tiny models →