What are the hardware requirements for Gpt2 Base Bne?

Gpt2 Base Bne requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gpt2 Base Bne and how large is it?

Gpt2 Base Bne is developed by PlanTL-GOB-ES. 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 Gpt2 Base Bne?

Gpt2 Base Bne is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gpt2 Base Bne by PlanTL-GOB-ES — VRAM 0.5GB

Name: Gpt2 Base Bne
Author: PlanTL-GOB-ES

Gpt2 Base Bne is an open-source language model by PlanTL-GOB-ES. Features: LLM, VRAM: 0.5GB, License: apache-2.0, LLM Explorer Score: 0.21.

Bne Dataset:bne Es Gpt2-base-bne National library of spain Region:us Spanish

Model Card on HF 🤗: https://huggingface.co/PlanTL-GOB-ES/gpt2-base-bne

Gpt2 Base Bne Parameters and Internals

Model Type

text generation

Use Cases

Areas:

text generation

Applications:

general use or fine-tuning for specific language tasks

Additional Notes

At the time of submission, no measures have been taken to estimate the bias and toxicity embedded in the model.

Supported Languages

Spanish (High proficiency)

Training Details

Data Sources:

National Library of Spain (BNE)

Data Volume:

570GB of clean and deduplicated text

Methodology:

Next token prediction with Byte-Pair Encoding (BPE)

Training Time:

3 days on 16 computing nodes with 4 NVIDIA V100 GPUs of 16GB VRAM each.

Hardware Used:

16 computing nodes, each with 4 NVIDIA V100 GPUs of 16GB VRAM

Model Architecture:

12-layer, 768-hidden, 12-heads

Input Output

Accepted Modalities:

text

LLM Name	Gpt2 Base Bne
Repository 🤗	https://huggingface.co/PlanTL-GOB-ES/gpt2-base-bne
Required VRAM	0.5 GB
Updated	2025-08-12
Maintainer	PlanTL-GOB-ES
Model Type	gpt2
Model Files	0.5 GB
Supported Languages	es
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Vocabulary Size	50261

Rank the Gpt2 Base Bne 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 Gpt2 Base Bne

Best Alternatives	Context / RAM	Downloads
Judge GPT2	0.5K / 0.4 GB	10
Hanuman	0K / 0.5 GB	17
BrtGPT 1 Pre	0K / 0.4 GB	132
GPT 2 Large 115K Steps	0K / 0 GB	11
GPT 2 Large 51K Steps	0K / 0 GB	7
GPT 2 Large 40K Steps	0K / 0 GB	10
GPT 2 Large 32K Steps	0K / 0 GB	12
GPT 2 Large 20K Steps	0K / 0 GB	9
GPT 2 Large 43K Steps	0K / 0 GB	8
Math Gpt2	0K / 0.5 GB	777