Lumina-2.75M needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Lumina‑2.75M: a tiny Italian language model for local inference
Lumina‑2.75M is a small language model with 2.75 million parameters. It is autoregressive and causal, trained from scratch for Italian. The model runs locally on any device with minimal resources.
Good at
- Coding assistance
- Local inference
- Low‑latency responses
Limits
- No vision support
- Limited context length of 165 tokens
- No external API dependencies
Best for
- Embedded devices
- Raspberry Pi projects
- Browser‑based demos
Who it’s for. Developers needing a lightweight Italian language model for offline use. It is suitable for hobbyists and professionals who want full control over data privacy.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → |
The only available GGUF file is 0.01 GB and requires about 0.5 GB of RAM at 8 k context. This is well within the limits of a laptop or Raspberry Pi. Use the provided quant for any device with at least 1 GB of RAM.
What GPU do you need for Lumina-2.75M?
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 (0.0 GB file, about 0.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Lumina-2.75M
How much VRAM does Lumina-2.75M need?
About 0.5 GB at its main file with an 8K context window. That is the 0.0 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-2.75M on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lumina-2.75M GGUF?
It depends on the quant: file is 0.0 GB.
What context length does Lumina-2.75M support?
The GGUF header lists a trained context length of 165 tokens (165). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.0 GB at 165.
Where can I download Lumina-2.75M GGUF?
The files are on Hugging Face in the jacopof/lumina-2.75m 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-2.75M 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‑2.75M on a device with 8 GB VRAM?
Yes, the model needs only 0.5 GB of RAM at 8 k context, so it will run on any device with 8 GB VRAM.
Does Lumina‑2.75M support other languages?
The model is trained for Italian only; no other languages are supported.
Is there a license restriction?
The model is released under the MIT license, allowing free use and modification.