What are the hardware requirements for Open Steuerllm?

Open Steuerllm requires approximately 56.2 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 Open Steuerllm and how large is it?

Open Steuerllm is developed by windprak, a model with 28b 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 Open Steuerllm?

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

Open Steuerllm by windprak — VRAM 56.2GB, 32K context

Name: Open Steuerllm
Author: windprak

Open Steuerllm is an open-source language model by windprak. Features: 28b LLM, VRAM: 56.2GB, Context: 32K, License: cc-by-nc-4.0, Instruction-Based, LLM Explorer Score: 0.22.

Arxiv:2602.11081 Conversational Dataset:windprak/steuerex Dataset:windprak/steuerllm ins... Dataset:windprak/steuerllm pre... De Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/windprak/open_steuerllm

Open Steuerllm Parameters and Internals

LLM Name	Open Steuerllm
Repository 🤗	https://huggingface.co/windprak/open_steuerllm
Model Size	28b
Required VRAM	56.2 GB
Updated	2026-07-27
Maintainer	windprak
Model Type	mistral
Instruction-Based	Yes
Model Files	4.8 GB: 1-of-12 4.8 GB: 2-of-12 4.8 GB: 3-of-12 4.9 GB: 4-of-12 4.8 GB: 5-of-12 4.8 GB: 6-of-12 4.9 GB: 7-of-12 4.8 GB: 8-of-12 4.8 GB: 9-of-12 4.9 GB: 10-of-12 4.8 GB: 11-of-12 3.1 GB: 12-of-12 0.0 GB
Supported Languages	de
Model Architecture	MistralForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.3
Tokenizer Class	LlamaTokenizerFast
Padding Token	</s>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Open Steuerllm 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 Open Steuerllm

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 28B Instruct V0.1	32K / 56.2 GB	113	0
Mistral 28B Instruct V0.2	32K / 56.2 GB	72	3