LU

Lumina-Next-135M

LuminaGGUF by jacopofUpdated 2026-11-01
Download on Hugging Face
Parameters122M
Context8K
Layers24
Architecturelumina_next
Smallest quant0.5 GB
Quick answer

Lumina-Next-135M needs about 1.1 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Lumina-Next-135M: Efficient 135M‑parameter model for edge devices

Lumina-Next-135M is a 135M‑parameter model built on the Lumina architecture. It supports long contexts up to 32,768 tokens and is specialized for Python coding, formal logic, and Italian language. The model is released under the MIT license.

Good at

  • Python coding
  • Formal logic tasks
  • Italian language

Limits

  • No vision support
  • Limited to 8,192–32,768 token contexts
  • Single‑headed architecture

Best for

  • Edge inference on laptops
  • Python code generation
  • Formal reasoning tasks

Who it’s for. Developers needing a lightweight model for local inference on consumer hardware. Ideal for applications that require long context handling and Italian language support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 1.1 GB
Fits Get file →

The available GGUF file is 0.49 GB and requires approximately 1.1 GB of VRAM at 8,192‑token context. For 8 GB VRAM, this quant is suitable. If VRAM is lower, consider a higher‑quantized version, but none is listed.

What GPU do you need for Lumina-Next-135M?

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 (0.5 GB file, about 1.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturelumina_next
Parameters122M
Layers24
Trained context8,192 tokens
KV cache (fp16)18 KB per token

Source

Quantized byjacopof
FamilyLumina
Licensemit
Downloads (HF)912
Last updated2026-11-01

Frequently asked questions about Lumina-Next-135M

How much VRAM does Lumina-Next-135M need?

About 1.1 GB at its main file with an 8K context window. That is the 0.5 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-Next-135M on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lumina-Next-135M GGUF?

It depends on the quant: file is 0.5 GB.

What context length does Lumina-Next-135M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download Lumina-Next-135M GGUF?

The files are on Hugging Face in the jacopof/lumina-next-135m 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-Next-135M 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-Next-135M on 8 GB VRAM?

Yes, the 0.49 GB GGUF file requires about 1.1 GB of VRAM at 8,192 tokens, fitting comfortably in 8 GB.

Does Lumina-Next-135M support vision tasks?

No, the model has no vision capabilities.

What context length can I use?

The native context is 8,192 tokens, extendable up to 32,768 tokens via YaRN.

Similar models

Browse all →

More from jacopof

All by jacopof →

More Lumina models

All Lumina →

Other tiny models

All tiny models →