What are the hardware requirements for GEITje 7B Chat GPTQ?

GEITje 7B Chat GPTQ requires approximately 4.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GEITje 7B Chat GPTQ and how large is it?

GEITje 7B Chat GPTQ is developed by TheBloke, a model with 7b 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 GEITje 7B Chat GPTQ?

GEITje 7B Chat GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GEITje 7B Chat GPTQ by TheBloke — VRAM 4.2GB, 32K context

Name: GEITje 7B Chat GPTQ
Author: TheBloke

GEITje 7B Chat GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:quantized:rijgersbe... Base model:rijgersberg/geitje-... Conversational Dataset:rijgersberg/no robots ... Dataset:rijgersberg/ultrachat ... Geitje Generated from trainer Gptq Mistral Nl Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/GEITje-7B-chat-GPTQ

GEITje 7B Chat GPTQ Parameters and Internals

Model Type

conversational

Use Cases

Areas:

research, commercial applications

Primary Use Cases:

conversation generation

Additional Notes

GEITje-chat is a finetuned version for dialogues and chat applications.

Supported Languages

Dutch (Fluent)

Training Details

Data Sources:

Dutch Gigacorpus, MADLAD-400

Data Volume:

10 billion tokens

Methodology:

Full-parameter finetune

Context Length:

8192

Model Architecture:

based on Mistral 7B

Input Output

Input Format:

<|user|> {prompt} <|assistant|>

Accepted Modalities:

text

Output Format:

text

LLM Name	GEITje 7B Chat GPTQ
Repository 🤗	https://huggingface.co/TheBloke/GEITje-7B-chat-GPTQ
Model Name	Geitje 7B Chat
Model Creator	Edwin Rijgersberg
Base Model(s)	GEITje 7B Chat Rijgersberg/GEITje-7B-chat
Model Size	7b
Required VRAM	4.2 GB
Updated	2026-08-08
Maintainer	TheBloke
Model Type	mistral
Model Files	4.2 GB
Supported Languages	nl
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the GEITje 7B Chat GPTQ 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 GEITje 7B Chat GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...enHermes 2.5 Mistral 7B Marlin	32K / 4.1 GB	6	2
Zephyr 7B Beta Marlin	32K / 4.1 GB	16	0
Mistral 7B Instruct V0.3 GPTQ	32K / 4.2 GB	113881	1
...ral 7B Instruct V0.3 GPTQ 4bit	32K / 4.2 GB	2946	18
...ral 7B Instruct V0.3 GPTQ 4bit	32K / 4.2 GB	2658	25
...istral 7B Pruned50 GPTQ Marlin	32K / 4 GB	5	0
Mistral 7B Instruct V0.2 GPTQ	32K / 4.2 GB	6743	56
Mistral 7B Unsloth Gptq 8bit	32K / 7.7 GB	7	0
Cosmosage V2	32K / 4.2 GB	8	4
...phyr 7B Beta Assistant V1 Gptq	32K / 4.2 GB	2	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/GEITje-7B-chat-GPTQ.