What are the hardware requirements for DElefant?

DElefant requires approximately 12.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DElefant and how large is it?

DElefant is developed by SebastianBodza. 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 DElefant?

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

DElefant by SebastianBodza — VRAM 12.5GB

Name: DElefant
Author: SebastianBodza

DElefant is an open-source language model by SebastianBodza. Features: LLM, VRAM: 12.5GB, License: cc-by-nc-sa-4.0, Instruction-Based, LLM Explorer Score: 0.07.

Bloom Dataset:sebastianbodza/ger wiz... De Endpoints compatible Instruct Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/SebastianBodza/DElefant

DElefant Parameters and Internals

Model Type

text generation

Additional Notes

The model is fine-tuned on an adapted BLOOM version with a translated and filtered dataset to leverage capabilities for various tasks including code generation.

Supported Languages

de (German)

Training Details

Data Sources:

SebastianBodza/Ger_WizardLM_evol_instruct_70k_V0

Methodology:

Full-Finetuning

Context Length:

2048

Hardware Used:

RTX 3090

Input Output

Input Format:

{instruction}\n\n### Response:

Accepted Modalities:

text

Output Format:

text

LLM Name	DElefant
Repository 🤗	https://huggingface.co/SebastianBodza/DElefant
Required VRAM	12.5 GB
Updated	2026-07-02
Maintainer	SebastianBodza
Model Type	bloom
Instruction-Based	Yes
Model Files	12.5 GB 0.0 GB
Supported Languages	de
Model Architecture	BloomForCausalLM
License	cc-by-nc-sa-4.0
Model Max Length	2048
Transformers Version	4.30.2
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50258
Torch Data Type	bfloat16
Errors	replace

Rank the DElefant 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 DElefant

Best Alternatives	Context / RAM	Downloads	Likes
Bloom 6b4 Clp German Instruct	0K / 13.8 GB	9	1
Bloomz 1b7 Instruct	0K / 3.4 GB	9	1
Bloomz 1b1 Instruct	0K / 4.3 GB	9	0