What are the hardware requirements for Pythia 14M Deduped?

Pythia 14M Deduped requires approximately 0.1 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 Pythia 14M Deduped and how large is it?

Pythia 14M Deduped is developed by EleutherAI, a model with 14m 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 Pythia 14M Deduped?

Pythia 14M Deduped is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Pythia 14M Deduped by EleutherAI — VRAM 0.1GB, 2K context

Name: Pythia 14M Deduped
Author: EleutherAI

Pythia 14M Deduped is an open-source language model by EleutherAI. Features: 14m LLM, VRAM: 0.1GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.12.

Arxiv:2101.00027 Arxiv:2201.07311 Arxiv:2304.01373 Dataset:eleutherai/pile Deploy:azure En Endpoints compatible Gpt neox Pythia Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/EleutherAI/pythia-14m-deduped

Pythia 14M Deduped Parameters and Internals

LLM Name	Pythia 14M Deduped
Repository 🤗	https://huggingface.co/EleutherAI/pythia-14m-deduped
Model Size	14m
Required VRAM	0.1 GB
Updated	2026-09-22
Maintainer	EleutherAI
Model Type	gpt_neox
Model Files	0.1 GB 0.1 GB
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.29.2
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	float16

Rank the Pythia 14M Deduped 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 Pythia 14M Deduped

Best Alternatives	Context / RAM	Downloads	Likes
Pythia 14M	2K / 0 GB	239461	6
Pythia 14m Sft	2K / 0.1 GB	5	0
...ythia 14M Finewebedu Sentences	2K / 0.1 GB	5	0
...t Llm Pythia 14M Pm Gen Ian Nd	2K / 0.1 GB	6	0
SmallLM	2K / 0 GB	38	1
Pythia 14M	2K / 0 GB	7	0
Tinyllama Random	2K / 0.1 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than EleutherAI/pythia-14m-deduped.