What are the hardware requirements for Mara Small?

Mara Small requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mara Small and how large is it?

Mara Small is developed by jaswanthsanjay88, a model with 28.8m 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 Mara Small?

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

Mara Small by jaswanthsanjay88 — VRAM 0.1GB

Name: Mara Small
Author: jaswanthsanjay88

Mara Small is an open-source language model by jaswanthsanjay88. Features: 28.8m LLM, VRAM: 0.1GB, License: apache-2.0, LLM Explorer Score: 0.31.

Dataset:roneneldan/tinystories En From-scratch Gpt Onnx Region:us Safetensors Small-language-model Tinystories

Model Card on HF 🤗: https://huggingface.co/jaswanthsanjay88/mara-small

Mara Small Parameters and Internals

LLM Name	Mara Small
Repository 🤗	https://huggingface.co/jaswanthsanjay88/mara-small
Model Size	28.8m
Required VRAM	0.1 GB
Updated	2026-08-28
Maintainer	jaswanthsanjay88
Model Files	0.1 GB
Supported Languages	en
License	apache-2.0
Vocabulary Size	8192

Rank the Mara Small 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