LU

Lumina-14M

LuminaGGUF by jacopofUpdated 2026-10-27
Download on Hugging Face
Parameters14M
Context256
Layers8
Architecturelumina
Smallest quant0.1 GB
Quick answer

Lumina-14M needs about 0.7 GB of memory at its main file (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Lumina‑14M: compact causal model with 14.4M parameters

Lumina‑14M is a 14.4‑million‑parameter causal language model. It offers a 256‑token context window and 8 transformer blocks with 384 channels. The model is lightweight, weighing only 55 MB in safetensors format.

Good at

  • coding
  • text generation
  • lightweight inference

Limits

  • 256‑token context
  • no vision support
  • MIT license

Best for

  • local code assistance
  • small‑scale text generation
  • offline inference on modest hardware

Who it’s for. Developers and researchers needing a small, fast language model that runs entirely offline. It is suitable for embedded systems or personal servers with limited resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 0.6 GB
Fits Get file →

The only available GGUF file is quantized as unknown, 0.06 GB in size, requiring approximately 0.7 GB of VRAM at 8 k context. This fits comfortably on 1 GB or larger GPUs. For tighter budgets, no alternative quantizations are provided.

What GPU do you need for Lumina-14M?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 the main file (0.1 GB file, about 0.7 GB in use).

Specifications

Architecture from the GGUF header

Architecturelumina
Parameters14M
Layers8
Trained context256 tokens
KV cache (fp16)12 KB per token

Source

Quantized byjacopof
FamilyLumina
Licensemit
Downloads (HF)593
Last updated2026-10-27

Frequently asked questions about Lumina-14M

How much VRAM does Lumina-14M need?

About 0.7 GB at its main file with an 8K context window. That is the 0.1 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-14M on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lumina-14M GGUF?

It depends on the quant: file is 0.1 GB.

What context length does Lumina-14M support?

The GGUF header lists a trained context length of 256 tokens (256). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 256.

Where can I download Lumina-14M GGUF?

The files are on Hugging Face in the jacopof/lumina-14m 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-14M use?

Hugging Face lists the license as mit. 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‑14M on 1 GB VRAM?

Yes, the GGUF file requires about 0.7 GB of VRAM at 8 k context, fitting within a 1 GB GPU.

Does Lumina‑14M support image inputs?

No, the model has no vision capabilities and only handles text.

Similar models

Browse all →

More from jacopof

All by jacopof →

More Lumina models

All Lumina →

Other tiny models

All tiny models →