LI

Lille 130m Instruct

LilleGGUF by NikityUpdated 2025-09-04
Download on Hugging Face
Parameters127M
Context512
Layers24
Architecturellama
Smallest quant0.1 GB
Quick answer

Lille 130m Instruct needs about 0.9 GB of memory at F16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q8_0) to 0.5 GB (F32).

Lille 130M Instruct – a compact instruction‑tuned language model

Lille 130M Instruct is a 127.17‑million‑parameter transformer decoder with GQA, RoPE, and RMSNorm. It is tuned on the Kyoto‑Corpus for instruction following and chat. The model is released under the apache‑2.0 license.

Good at

  • Instruction following
  • Chat interactions
  • Text completion

Limits

  • 512‑token context
  • No vision support
  • Requires 8‑bit or higher quantization for low VRAM

Best for

  • Lightweight chatbots
  • Instruction‑driven scripts
  • Quick prototyping

Who it’s for. Developers and researchers needing a small, open‑source LLM that can run on modest hardware. The model is ideal for those who want to fine‑tune or integrate an instruction‑tuned model without large GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.3 GB 0.8 GB
Fits Get file →
F320.5 GB 1.0 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.14 GB file, 0.7 GB memory at 8k context). For 4 GB VRAM, F16 (0.26 GB file, 0.9 GB memory) is the smallest available. F32 (0.51 GB file, 1.1 GB memory) offers full precision but needs more memory.

What GPU do you need for Lille 130m Instruct?

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 F32 (0.5 GB file, about 1.1 GB in use).

Which Lille 130m Instruct quant should you choose?

F16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters127M
Layers24
Trained context512 tokens
KV cache (fp16)12 KB per token

Source

Quantized byNikity
FamilyLille
Licenseapache-2.0
Downloads (HF)638
Last updated2025-09-04

Frequently asked questions about Lille 130m Instruct

How much VRAM does Lille 130m Instruct need?

About 0.9 GB at F16 with an 8K context window. That is the 0.3 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 Lille 130m Instruct on an 8 GB GPU?

Yes, with F32: 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 Lille 130m Instruct GGUF?

It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.3 GB, F32 is 0.5 GB.

What context length does Lille 130m Instruct support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.

Where can I download Lille 130m Instruct GGUF?

The files are on Hugging Face in the Nikity/lille-130m-instruct repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Lille 130m Instruct 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 Lille 130M Instruct on 8 GB VRAM?

Yes, the Q8_0 quantized model uses 0.7 GB memory at 8k context, fitting comfortably on 8 GB VRAM.

Does the model support vision tasks?

No, Lille 130M Instruct is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license, allowing free use and modification.

Similar models

Browse all →

Other tiny models

All tiny models →