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
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 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
Source
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.