What are the hardware requirements for Tucano 2b4 Instruct?

Tucano 2b4 Instruct requires approximately 9.8 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 Tucano 2b4 Instruct and how large is it?

Tucano 2b4 Instruct is developed by TucanoBR, a model with 2.4b 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 Tucano 2b4 Instruct?

Tucano 2b4 Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tucano 2b4 Instruct by TucanoBR — VRAM 9.8GB, 4K context

Name: Tucano 2b4 Instruct
Author: TucanoBR

Tucano 2b4 Instruct is an open-source language model by TucanoBR. Features: 2.4b LLM, VRAM: 9.8GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

Arxiv:2411.07854 Base model:finetune:tucanobr/t... Base model:tucanobr/tucano-2b4 Co2 eq emissions Conversational Dataset:cnmoro/gpt4-500k-augme... Dataset:nicholaskluge/instruct... Dataset:nicholaskluge/reward-a... Dataset:rhaymison/orca-math-po... Deploy:azure Endpoints compatible Instruct Llama Model-index Pt Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TucanoBR/Tucano-2b4-Instruct

Tucano 2b4 Instruct Parameters and Internals

LLM Name	Tucano 2b4 Instruct
Repository 🤗	https://huggingface.co/TucanoBR/Tucano-2b4-Instruct
Base Model(s)	Tucano 2b4 TucanoBR/Tucano-2b4
Model Size	2.4b
Required VRAM	9.8 GB
Updated	2026-05-04
Maintainer	TucanoBR
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 4.8 GB: 2-of-2 5.0 GB: 1-of-2 4.8 GB: 2-of-2
Supported Languages	pt
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.44.2
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	32002
Torch Data Type	float32

Rank the Tucano 2b4 Instruct 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 Tucano 2b4 Instruct

Best Alternatives	Context / RAM	Downloads	Likes
...NE 3.5 2.4B Instruct Llamafied	32K / 5.3 GB	761	6
YuLan Mini Instruct	28K / 4.8 GB	220	8

Note: green Score (e.g. "73.2") means that the model is better than TucanoBR/Tucano-2b4-Instruct.