What are the hardware requirements for Pythia 2.8B Deduped?

Pythia 2.8B Deduped requires approximately 5.7 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 2.8B Deduped and how large is it?

Pythia 2.8B Deduped is developed by EleutherAI, a model with 2.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Pythia 2.8B Deduped perform on standard benchmarks?

Pythia 2.8B Deduped has the following published scores: MMLU 26.78. Compare against reference models on this page or on the LLM Explorer leaderboards.

Pythia 2.8B Deduped by EleutherAI — VRAM 5.7GB, 2K context

Name: Pythia 2.8B Deduped
Author: EleutherAI

Pythia 2.8B Deduped is an open-source language model by EleutherAI. Features: 2.8b LLM, VRAM: 5.7GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 36.3, HellaSwag: 60.7, MMLU: 26.8, GSM8K: 0.8.

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

Model Card on HF 🤗: https://huggingface.co/EleutherAI/pythia-2.8b-deduped

Pythia 2.8B Deduped Parameters and Internals

Model Type

Transformer-based Language Model

Use Cases

Areas:

Research

Applications:

Interpretability research

Primary Use Cases:

Scientific experiments on language models, Promoting interpretability research

Limitations:

Not suitable for deployment, Not suitable for translation or generating text in languages other than English

Considerations:

Please conduct your own risk and bias assessment when applying the model.

Additional Notes

Please note that all models in the *Pythia* suite were renamed in January 2023.

Training Details

Data Sources:

EleutherAI/the_pile_deduplicated

LLM Name	Pythia 2.8B Deduped
Repository 🤗	https://huggingface.co/EleutherAI/pythia-2.8b-deduped
Model Size	2.8b
Required VRAM	5.7 GB
Updated	2026-08-01
Maintainer	EleutherAI
Model Type	gpt_neox
Model Files	5.7 GB 5.7 GB
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.24.0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	float16

Rank the Pythia 2.8B 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

Quantized Models of the Pythia 2.8B Deduped

Model	Likes	Downloads	VRAM
Pythia 2.8B Deduped GPTQ	0	11	1 GB

Best Alternatives to Pythia 2.8B Deduped

Best Alternatives	Context / RAM	Downloads	Likes
Statichh Pythia 2.8B Sft Bf16	2K / 11.1 GB	8	0
Pythia 2.8B Thai Base V1	2K / 5.9 GB	146	2
Hh Full	2K / 11.1 GB	6	0
... Llm Pythia 2.8B Pm Gen Ian Nd	2K / 11.1 GB	5	0
...thia 2.8B Mitchell Sft Hh Rlhf	2K / 11.1 GB	14	0
Pythia 2.8B Sft Hh Rlhf	2K / 5.6 GB	7	0
Pythia 2.8B	2K / 5.7 GB	45869	35
TLDR Pythia2.8B SFT	2K / 11.1 GB	7	0
...ythia 2.8B Helpful Sft 3epochs	2K / 5.6 GB	5	0
Indication PYT V2	2K / 5.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than EleutherAI/pythia-2.8b-deduped.