What are the hardware requirements for Tinystories 25M?

Tinystories 25M requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tinystories 25M and how large is it?

Tinystories 25M is developed by epoyraz, a model with 25m 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 Tinystories 25M?

Tinystories 25M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tinystories 25M by epoyraz — VRAM 0.1GB

Name: Tinystories 25M
Author: epoyraz

Tinystories 25M is an open-source language model by epoyraz. Features: 25m LLM, VRAM: 0.1GB, License: mit, LLM Explorer Score: 0.24.

Arxiv:2104.09864 Arxiv:2305.07759 Arxiv:2305.13245 Arxiv:2412.19437 Dataset:roneneldan/tinystories En From-scratch Gpt Multi-token-prediction Muon Pytorch Qk-norm Region:us Rope Tinystories

Model Card on HF 🤗: https://huggingface.co/epoyraz/tinystories-25m

Tinystories 25M Parameters and Internals

LLM Name	Tinystories 25M
Repository 🤗	https://huggingface.co/epoyraz/tinystories-25m
Model Size	25m
Required VRAM	0.1 GB
Updated	2026-07-29
Maintainer	epoyraz
Model Files	0.1 GB
Supported Languages	en
License	mit
Vocabulary Size	16384

Rank the Tinystories 25M 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