What are the hardware requirements for Leo Hessianai 13B Chat?

Leo Hessianai 13B Chat requires approximately 26 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Leo Hessianai 13B Chat and how large is it?

Leo Hessianai 13B Chat is developed by LeoLM, a model with 13b 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 Leo Hessianai 13B Chat?

Leo Hessianai 13B Chat is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Leo Hessianai 13B Chat by LeoLM — VRAM 26GB, 8K context

Name: Leo Hessianai 13B Chat
Author: LeoLM

Leo Hessianai 13B Chat is an open-source language model by LeoLM. Features: 13b LLM, VRAM: 26GB, Context: 8K, Instruction-Based, LLM Explorer Score: 0.09.

Conversational Custom code Dataset:freedomintelligence/al... Dataset:freedomintelligence/ev... Dataset:leolm/german poems Dataset:leolm/german songs Dataset:leolm/openschnabeltier Dataset:openassistant/oasst-de De En Endpoints compatible Instruct Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/LeoLM/leo-hessianai-13b-chat

Leo Hessianai 13B Chat Parameters and Internals

Model Type

Causal decoder-only transformer language model

Use Cases

Areas:

Open source, Commercial research

Limitations:

Performance on math and advanced reasoning tasks is suboptimal.

Considerations:

The model may produce biased or undesirable outputs.

Supported Languages

en (unknown), de (unknown)

Training Details

Data Sources:

LeoLM/OpenSchnabeltier, OpenAssistant/OASST-DE, FreedomIntelligence/alpaca-gpt4-deutsch, FreedomIntelligence/evol-instruct-deutsch, LeoLM/German_Poems, LeoLM/German_Songs

Data Volume:

132,540 samples, 67,530,728 tokens

Methodology:

Continued pretraining and finetuning on instruction datasets

Context Length:

8192

Hardware Used:

HessianAI's supercomputer 42

Model Architecture:

Causal decoder-only transformer

Input Output

Input Format:

ChatML format

Accepted Modalities:

text

LLM Name	Leo Hessianai 13B Chat
Repository 🤗	https://huggingface.co/LeoLM/leo-hessianai-13b-chat
Model Size	13b
Required VRAM	26 GB
Updated	2026-07-26
Maintainer	LeoLM
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Supported Languages	en de
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.33.1
Tokenizer Class	LlamaTokenizer
Padding Token	<PAD>
Vocabulary Size	32128
Torch Data Type	float16

Rank the Leo Hessianai 13B Chat 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

Quantized Models of the Leo Hessianai 13B Chat

Model	Likes	Downloads	VRAM
Leo Hessianai 13B Chat GGUF	7	430	5 GB
Leo Hessianai 13B Chat GPTQ	1	47	7 GB
Leo Hessianai 13B Chat AWQ	1	6	7 GB

Best Alternatives to Leo Hessianai 13B Chat

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
NexusRaven 13B	16K / 26 GB	37	106
Panda Coder 13B	16K / 26 GB	11	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	8	28
Gen Sim	16K / 0.3 GB	4	3
Llama 3 13B Instruct Ft	8K / 26.1 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than LeoLM/leo-hessianai-13b-chat.