What are the hardware requirements for Scribe?

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

Who developed Scribe and how large is it?

Scribe is developed by mbsdeepak, a model with 30m 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 Scribe?

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

Scribe by mbsdeepak — VRAM 0.1GB

Name: Scribe
Author: mbsdeepak

Scribe is an open-source language model by mbsdeepak. Features: 30m LLM, VRAM: 0.1GB, License: mit, LLM Explorer Score: 0.31.

Dataset:roneneldan/tinystories From-scratch Gpt Language-model Pytorch Region:us Safetensors Slm Tinystories

Model Card on HF 🤗: https://huggingface.co/mbsdeepak/scribe

Scribe Parameters and Internals

LLM Name	Scribe
Repository 🤗	https://huggingface.co/mbsdeepak/scribe
Model Size	30m
Required VRAM	0.1 GB
Updated	2026-08-18
Maintainer	mbsdeepak
Model Files	0.1 GB
License	mit
Vocabulary Size	50257

Rank the Scribe 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