What are the hardware requirements for GEITje 7B Chat V2?

GEITje 7B Chat V2 requires 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 V2 and how large is it?

GEITje 7B Chat V2 is developed by Rijgersberg, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does GEITje 7B Chat V2 perform on standard benchmarks?

GEITje 7B Chat V2 has the following published scores: MMLU 49. Compare against reference models on this page or on the LLM Explorer leaderboards.

GEITje 7B Chat V2 by Rijgersberg — 32K context

Name: GEITje 7B Chat V2
Author: Rijgersberg

GEITje 7B Chat V2 is an open-source language model by Rijgersberg. Features: 7b LLM, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.13, Arc: 50.3, HellaSwag: 74.1, MMLU: 49, GSM8K: 16.2.

Base model:finetune:rijgersber... Base model:rijgersberg/geitje-... Conversational Dataset:bramvanroy/dutch chat ... Dataset:rijgersberg/no robots ... Dataset:rijgersberg/ultrachat ... Endpoints compatible Geitje Generated from trainer Mistral Nl Region:us Safetensors Tensorboard

Model Card on HF 🤗: https://huggingface.co/Rijgersberg/GEITje-7B-chat-v2

GEITje 7B Chat V2 Parameters and Internals

Model Type

text-generation, conversational

Use Cases

Areas:

text generation, conversational applications

Applications:

research, commercial applications

Primary Use Cases:

Instructions following, question answering, dialogues on various topics

Additional Notes

This model has been further trained on Dutch texts to improve its proficiency in the Dutch language and knowledge on Dutch topics.

Supported Languages

nl (Dutch (primary))

Training Details

Data Sources:

Rijgersberg/no_robots_nl, Rijgersberg/ultrachat_10k_nl, BramVanroy/dutch_chat_datasets, Dutch Gigacorpus, MADLAD-400

Data Volume:

10 billion tokens

Methodology:

Full-parameter finetune

Context Length:

8192

Model Architecture:

Based on Mistral 7B

LLM Name	GEITje 7B Chat V2
Repository 🤗	https://huggingface.co/Rijgersberg/GEITje-7B-chat-v2
Base Model(s)	GEITje 7B Rijgersberg/GEITje-7B
Model Size	7b
Required VRAM	0 GB
Updated	2026-08-03
Maintainer	Rijgersberg
Model Type	mistral
Model Files	0.0 GB
Supported Languages	nl
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the GEITje 7B Chat V2 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 V2

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8470	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8018	17
Hebrew Mistral 7B 200K	256K / 30 GB	23	15
Astral 256K 7B	250K / 14.4 GB	9	0
Astral 256K 7B V2	250K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than Rijgersberg/GEITje-7B-chat-v2.