What are the hardware requirements for Gervasio 7B Portuguese Ptpt Decoder?

Gervasio 7B Portuguese Ptpt Decoder requires approximately 13.5 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 Gervasio 7B Portuguese Ptpt Decoder and how large is it?

Gervasio 7B Portuguese Ptpt Decoder is developed by PORTULAN, 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 Gervasio 7B Portuguese Ptpt Decoder?

Gervasio 7B Portuguese Ptpt Decoder is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gervasio 7B Portuguese Ptpt Decoder by PORTULAN — VRAM 13.5GB, 4K context

Name: Gervasio 7B Portuguese Ptpt Decoder
Author: PORTULAN

Gervasio 7B Portuguese Ptpt Decoder is an open-source language model by PORTULAN. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.1.

Arxiv:2402.18766 Albertina-pt* Clm Dataset:portulan/extraglue Dataset:portulan/extraglue-ins... Decoder Endpoints compatible Foundation model Gervasio-7b-portuguese-ptbr-de... Gervasio-7b-portuguese-ptpt-de... Gervasio-pt* Gervasio-ptbr Gervasio-ptpt Gpt Instruct Llama Portuguese Portulan Pt Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/PORTULAN/gervasio-7b-portuguese-ptpt-decoder

Gervasio 7B Portuguese Ptpt Decoder Parameters and Internals

Model Type

decoder

Use Cases

Areas:

Research, Commercial applications

Applications:

Text generation, Language modeling

Primary Use Cases:

Portuguese text generation

Limitations:

The model is conditioned for Portuguese and may not perform well with other languages.

Additional Notes

Developed by a team from University of Lisbon. Can be used for free under an open license.

Supported Languages

Portuguese (proficient)

Training Details

Data Sources:

PORTULAN/extraglue, PORTULAN/extraglue-instruct

Methodology:

Supervised fine-tuning with causal language modeling objective and data augmentation techniques.

Context Length:

512

Model Architecture:

Transformer, hidden size of 4096, intermediate size of 11008, 32 attention heads, 32 hidden layers, Byte-Pair Encoding tokenizer with a vocabulary size of 32,000.

Input Output

Input Format:

Text

Accepted Modalities:

text

Output Format:

Text

LLM Name	Gervasio 7B Portuguese Ptpt Decoder
Repository 🤗	https://huggingface.co/PORTULAN/gervasio-7b-portuguese-ptpt-decoder
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-07-29
Maintainer	PORTULAN
Model Type	llama
Instruction-Based	Yes
Model Files	13.5 GB 13.5 GB
Supported Languages	pt
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Gervasio 7B Portuguese Ptpt Decoder 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 Gervasio 7B Portuguese Ptpt Decoder

Best Alternatives	Context / RAM	Downloads	Likes
124	1024K / 16.1 GB	93	0
A5.4	1024K / 16.1 GB	12	0
A3.4	1024K / 16.1 GB	13	0
A2.4	1024K / 16.1 GB	12	0
... Qwen2.5llamaify 7B V23.1 200K	195K / 15.2 GB	29	5
Salamandra 7B Instruct 2606	160K / 15.6 GB	599	2
SuperNeuralDreadDevil 8B	128K / 16.1 GB	10	1
Falcon3 7B Instruct	32K / 14.8 GB	11749	80
Falcon3 Jessi V0.4 7B Slerp	32K / 14.9 GB	34	9
Jessi V0.4 Falcon3 7B Instruct	32K / 14.8 GB	22	0

Note: green Score (e.g. "73.2") means that the model is better than PORTULAN/gervasio-7b-portuguese-ptpt-decoder.