What are the hardware requirements for GPT Neo 33M Simplewiki 2048 Scratch?

GPT Neo 33M Simplewiki 2048 Scratch requires approximately 0.3 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 33M Simplewiki 2048 Scratch and how large is it?

GPT Neo 33M Simplewiki 2048 Scratch is developed by pszemraj, a model with 33m 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 GPT Neo 33M Simplewiki 2048 Scratch?

GPT Neo 33M Simplewiki 2048 Scratch is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GPT Neo 33M Simplewiki 2048 Scratch by pszemraj — VRAM 0.3GB, 2K context

Name: GPT Neo 33M Simplewiki 2048 Scratch
Author: pszemraj

GPT Neo 33M Simplewiki 2048 Scratch is an open-source language model by pszemraj. Features: 33m LLM, VRAM: 0.3GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.09.

Base model:finetune:roneneldan... Base model:roneneldan/tinystor... Dataset:pszemraj/simple wikipe... En Endpoints compatible Generated from trainer Gpt neo Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/pszemraj/GPT-Neo-33M-simplewiki-2048-scratch

GPT Neo 33M Simplewiki 2048 Scratch Parameters and Internals

Model Type

text-generation

Supported Languages

en (Supported)

Training Details

Data Sources:

pszemraj/simple_wikipedia_LM

Context Length:

2048

LLM Name	GPT Neo 33M Simplewiki 2048 Scratch
Repository 🤗	https://huggingface.co/pszemraj/GPT-Neo-33M-simplewiki-2048-scratch
Base Model(s)	TinyStories 33M roneneldan/TinyStories-33M
Model Size	33m
Required VRAM	0.3 GB
Updated	2026-07-14
Maintainer	pszemraj
Model Type	gpt_neo
Model Files	0.3 GB 0.0 GB
Supported Languages	en
Model Architecture	GPTNeoForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.33.1
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50257
Torch Data Type	float32
Activation Function	gelu_new
Errors	replace

Rank the GPT Neo 33M Simplewiki 2048 Scratch 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 33M Simplewiki 2048 Scratch

Best Alternatives	Context / RAM	Downloads	Likes
TinyStories 33M	2K / 0.3 GB	12627	112
TinyStories 33M Ds	2K / GB	7	0
TinyStories Instruct 33M	2K / 0.3 GB	2599	10
...Tinystories 33M Epoch10 Merged	2K / 0.3 GB	15	2
TinyStories 33M Finetuned	2K / 0.3 GB	12	0
TinyStories 2Layers 33M	2K / 0.3 GB	510	5
...nyStories Instruct 2Layers 33M	2K / 0.3 GB	346	7

Note: green Score (e.g. "73.2") means that the model is better than pszemraj/GPT-Neo-33M-simplewiki-2048-scratch.