What are the hardware requirements for Llama2 15M Tinystories?

Llama2 15M Tinystories requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama2 15M Tinystories and how large is it?

Llama2 15M Tinystories is developed by Kepler182ab, a model with 15m 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 Llama2 15M Tinystories?

Llama2 15M Tinystories is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama2 15M Tinystories by Kepler182ab — VRAM 0.1GB

Name: Llama2 15M Tinystories
Author: Kepler182ab

Llama2 15M Tinystories is an open-source language model by Kepler182ab. Features: 15m LLM, VRAM: 0.1GB, License: mit, LLM Explorer Score: 0.31.

Arxiv:2305.07759 Dataset:roneneldan/tinystories En From-scratch Llama2 Pytorch Region:us Safetensors Story-generation Tinystories

Model Card on HF 🤗: https://huggingface.co/Kepler182ab/llama2-15m-tinystories

Llama2 15M Tinystories Parameters and Internals

LLM Name	Llama2 15M Tinystories
Repository 🤗	https://huggingface.co/Kepler182ab/llama2-15m-tinystories
Model Size	15m
Required VRAM	0.1 GB
Updated	2026-10-11
Maintainer	Kepler182ab
Model Files	0.1 GB
Supported Languages	en
License	mit
Vocabulary Size	32000

Rank the Llama2 15M Tinystories 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