What are the hardware requirements for Brahe?

Brahe requires approximately 26 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Brahe and how large is it?

Brahe is developed by Pclanglais, 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 Brahe?

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

Brahe by Pclanglais — VRAM 26GB, 4K context

Name: Brahe
Author: Pclanglais

Brahe is an open-source language model by Pclanglais. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: cc0-1.0, LLM Explorer Score: 0.09.

Dataset:pclanglais/brahe-novel... En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Pclanglais/Brahe

Brahe Parameters and Internals

Model Type

analytical LLM, text-analysis

Use Cases

Areas:

computational humanities

Applications:

annotation of literary texts

Primary Use Cases:

generate a list of annotations for given text

Limitations:

works best on languages included in llama-13B training

Additional Notes

Brahe is a model inspired by characters from Daniele del Giudice's philosophical novel 'Atlante occidentale'.

Supported Languages

English (native), French (native), German (native), Italian (native), Occitan (Gascon variety) (native)

Training Details

Data Sources:

8,000 excerpts of literature in the public domain, synthetic and manual annotations

Data Volume:

8,000 excerpts

Methodology:

fine-tuned from llama-13B

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

annotations for literature

LLM Name	Brahe
Repository 🤗	https://huggingface.co/Pclanglais/Brahe
Model Size	13b
Required VRAM	26 GB
Updated	2026-07-28
Maintainer	Pclanglais
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	cc0-1.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.34.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Brahe 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 Brahe

Best Alternatives	Context / RAM	Downloads	Likes
Luminaura RP 13B	128K / 26 GB	9	1
Yarn Llama 2 13B 128K	128K / 26 GB	184	113
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	5	0
LongAlign 13B 64K	64K / 26 GB	96	13
LongAlign 13B 64K Base	64K / 26 GB	89	3
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	4	4
Openbuddy Llama2 13b64k V15	64K / 26.1 GB	12	2

Note: green Score (e.g. "73.2") means that the model is better than Pclanglais/Brahe.