LI

lilbase

LilbaseGGUF by navthingsUpdated 2026-09-26
Download on Hugging Face
Parameters297M
Context1K
Layers24
Architecturellama
Smallest quant0.3 GB
Quick answer

lilbase needs about 1.0 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB (Q4_K_M) to 0.4 GB (Q8_0).

Lilbase – a 297 M parameter llama‑style base model

Lilbase is a 297 M parameter llama‑style base model trained from scratch on a Kaggle TPU v5e‑8. It continues text rather than answering questions. The model uses a 24‑layer architecture with 1024 hidden size, 16 query heads, 4 kv heads, and a 1024‑token context window.

Good at

  • Text continuation
  • Grammar‑solid output
  • Fast inference on modest hardware

Limits

  • No vision support
  • No chat‑specific prompt handling
  • License not specified

Best for

  • Generating prose snippets
  • Fine‑tuning for custom tasks
  • Embedding generation

Who it’s for. Developers and researchers who need a lightweight llama‑style base model for text generation or fine‑tuning. It is suitable for environments with limited GPU memory and for users who prefer open‑source models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 0.8 GB
Fits Get file →
Q8_00.4 GB 0.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.27 GB file, ~1 GB memory at 8k context). For 12 GB VRAM, Q8_0 (0.38 GB file, ~1.1 GB memory at 8k context) provides higher precision.

What GPU do you need for lilbase?

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 Q8_0 (0.4 GB file, about 1.1 GB in use).

Which lilbase quant should you choose?

Q4_K_M is the usual starting point for lilbase: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.4 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters297M
Layers24
Trained context1,024 tokens
KV cache (fp16)24 KB per token

Source

Quantized bynavthings
FamilyLilbase
Downloads (HF)274
Last updated2026-09-26

Frequently asked questions about lilbase

How much VRAM does lilbase need?

About 1.0 GB at Q4_K_M 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 lilbase on an 8 GB GPU?

Yes, with Q8_0: the 0.4 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 lilbase GGUF?

It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.4 GB.

What context length does lilbase support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 1K.

Where can I download lilbase GGUF?

The files are on Hugging Face in the navthings/lilbase repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Lilbase on 8 GB VRAM?

Yes, the Q4_K_M quantized file is 0.27 GB and requires about 1 GB of VRAM at 8k context.

Does Lilbase support vision tasks?

No, Lilbase is a text‑only model with no vision capabilities.

Similar models

Browse all →

More from navthings

All by navthings →

More Lilbase models

All Lilbase →

Other tiny models

All tiny models →