What are the hardware requirements for Based 360M?

Based 360M requires approximately 1.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Based 360M and how large is it?

Based 360M is developed by hazyresearch, a model with 360m 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 Based 360M?

Based 360M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Based 360M by hazyresearch — VRAM 1.4GB

Name: Based 360M
Author: hazyresearch

Based 360M is an open-source language model by hazyresearch. Features: 360m LLM, VRAM: 1.4GB, License: mit, LLM Explorer Score: 0.11.

Arxiv:2402.18668 Dataset:eleutherai/pile En Endpoints compatible Gpt2 Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/hazyresearch/based-360m

Based 360M Parameters and Internals

LLM Name	Based 360M
Repository 🤗	https://huggingface.co/hazyresearch/based-360m
Model Size	360m
Required VRAM	1.4 GB
Updated	2026-10-30
Maintainer	hazyresearch
Model Type	gpt2
Model Files	1.4 GB
Supported Languages	en
License	mit
Transformers Version	4.36.2
Vocabulary Size	50257
Activation Function	swiglu

Rank the Based 360M 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