What are the hardware requirements for GPT Neo 1.3B?

GPT Neo 1.3B requires approximately 5.3 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GPT Neo 1.3B and how large is it?

GPT Neo 1.3B is developed by EleutherAI, a model with 1.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does GPT Neo 1.3B perform on standard benchmarks?

GPT Neo 1.3B has the following published scores: MMLU 24.82. Compare against reference models on this page or on the LLM Explorer leaderboards.

GPT Neo 1.3B by EleutherAI — VRAM 5.3GB, 2K context

Name: GPT Neo 1.3B
Author: EleutherAI

GPT Neo 1.3B is an open-source language model by EleutherAI. Features: 1.3b LLM, VRAM: 5.3GB, Context: 2K, License: mit, LLM Explorer Score: 0.11, Arc: 31.2, HellaSwag: 48.5, MMLU: 24.8, GSM8K: 0.5.

Arxiv:2101.00027 Dataset:eleutherai/pile Deploy:azure En Endpoints compatible Gpt neo Jax Pytorch Region:us Rust Safetensors

Model Card on HF 🤗: https://huggingface.co/EleutherAI/gpt-neo-1.3B

GPT Neo 1.3B Parameters and Internals

Model Type

text generation, causal-lm

Use Cases

Areas:

text generation, research

Limitations:

May produce socially unacceptable content, Requires curation for quality and safety

Considerations:

Human curation is recommended

Additional Notes

Evaluation results show competitive performance in multiple areas.

Supported Languages

en (fluent)

Training Details

Data Sources:

EleutherAI/pile

Data Volume:

380 billion tokens

Methodology:

trained as a masked autoregressive language model using cross-entropy loss

Training Time:

362,000 steps

Model Architecture:

transformer

Safety Evaluation

Risk Categories:

profanity, lewd language

Ethical Considerations:

Model may produce socially unacceptable text

Responsible Ai Considerations

Accountability:

Users should curate/filter outputs

Input Output

Input Format:

Prompts in text format

Accepted Modalities:

text

Output Format:

Generated text sequences

LLM Name	GPT Neo 1.3B
Repository 🤗	https://huggingface.co/EleutherAI/gpt-neo-1.3B
Model Size	1.3b
Required VRAM	5.3 GB
Updated	2026-08-06
Maintainer	EleutherAI
Model Type	gpt_neo
Model Files	5.3 GB 5.3 GB
Supported Languages	en
Model Architecture	GPTNeoForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.9.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	50257
Activation Function	gelu_new

Rank the GPT Neo 1.3B 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

Best Alternatives to GPT Neo 1.3B

Best Alternatives	Context / RAM	Downloads	Likes
GPT NEO 1.3B Wiki	2K / 5.3 GB	13	1
...ni Neo 1.3B Mental Health Lora	2K / 1.6 GB	82	2
GPT Neo 1.3B Lama	2K / 5.3 GB	6	0
GPT Neo 1.3B Alpaca	2K / 5.3 GB	5	0
Adonalsium GPT Neo 1.3B	2K / 0 GB	1	1
GPT Neo 1.3B Cs Finetuning	2K / 0.5 GB	5	0
GPT NeoX 1.3B Viet Long 70	2K / 5.3 GB	7	0
...oX 1.3B Viet Custom 30 General	2K / 5.3 GB	5	0
GPT NeoX 1.3B Viet Custom 30	2K / 5.3 GB	9	0
GPT NeoX 1.3B Viet Custom 10	2K / 5.3 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than EleutherAI/gpt-neo-1.3B.