What are the hardware requirements for Lilbase?

Lilbase requires approximately 0.3 GB of VRAM and supports a context window of 1K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lilbase and how large is it?

Lilbase is developed by navthings, a model with 297m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Lilbase?

Lilbase is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lilbase by navthings — VRAM 0.3GB, 1K context

Name: Lilbase
Author: navthings

Lilbase is an open-source language model by navthings. Features: 297m LLM, VRAM: 0.3GB, Context: 1K, Quantized, LLM Explorer Score: 0.3.

Base-model Conversational Dataset:huggingfacefw/fineweb-... En Endpoints compatible Gguf Llama Q4 Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/navthings/lilbase

Lilbase Parameters and Internals

LLM Name	Lilbase
Repository 🤗	https://huggingface.co/navthings/lilbase
Model Size	297m
Required VRAM	0.3 GB
Updated	2026-09-28
Maintainer	navthings
Model Type	llama
Model Files	0.3 GB 0.4 GB 1.2 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	q4\|gguf\|q4_k
Model Architecture	LlamaForCausalLM
Context Length	1024
Model Max Length	1024
Transformers Version	5.17.0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000

Rank the Lilbase capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Lilbase

Model	Likes	Downloads	VRAM
Lilchat	1	514	0 GB

Best Alternatives to Lilbase

Best Alternatives	Context / RAM	Downloads	Likes
Lilchat	1K / 0.3 GB	514	1

Note: green Score (e.g. "73.2") means that the model is better than navthings/lilbase.