What are the hardware requirements for FLOR 1.3B Instructed?

FLOR 1.3B Instructed requires approximately 2.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed FLOR 1.3B Instructed and how large is it?

FLOR 1.3B Instructed is developed by projecte-aina, a model with 1.3b 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 FLOR 1.3B Instructed?

FLOR 1.3B Instructed is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

FLOR 1.3B Instructed by projecte-aina — VRAM 2.6GB

Name: FLOR 1.3B Instructed
Author: projecte-aina

FLOR 1.3B Instructed is an open-source language model by projecte-aina. Features: 1.3b LLM, VRAM: 2.6GB, License: apache-2.0, LLM Explorer Score: 0.1.

Bloom Endpoints compatible Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/projecte-aina/FLOR-1.3B-Instructed

FLOR 1.3B Instructed Parameters and Internals

Model Type

transformer, causal language model, text generation

Use Cases

Areas:

Research, Commercial Applications

Primary Use Cases:

text generation, summarization, question answering, creative writing

Supported Languages

Catalan (high), Spanish (high), English (high)

Training Details

Data Sources:

InstruCat, Dolly, MENTOR_ES, MENTOR_CA

Data Volume:

140B tokens

Methodology:

language adaptation technique performed on BLOOM-7.1B

Model Architecture:

transformer-based

Responsible Ai Considerations

Fairness:

The model may have biases due to data collection methods.

Accountability:

Users are responsible for complying with applicable regulations and risk mitigation.

Mitigation Strategies:

Research in bias and toxicity is intended for the future.

Input Output

Input Format:

### Instruction\n{instruction}\n### Context\n{context}\n### Answer\n

Accepted Modalities:

text

Output Format:

text

LLM Name	FLOR 1.3B Instructed
Repository 🤗	https://huggingface.co/projecte-aina/FLOR-1.3B-Instructed
Model Size	1.3b
Required VRAM	2.6 GB
Updated	2026-08-06
Maintainer	projecte-aina
Model Type	bloom
Model Files	2.6 GB
Model Architecture	BloomForCausalLM
License	apache-2.0
Transformers Version	4.28.1
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50257
Torch Data Type	float16
Errors	replace

Rank the FLOR 1.3B Instructed 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 FLOR 1.3B Instructed

Best Alternatives	Context / RAM	Downloads	Likes
FLOR 1.3B Xat	0K / 2.6 GB	7	0
Carballo Finetuned	0K / 5.3 GB	434	0
RAGGFlor1.3	0K / 2.6 GB	8	0
RAGFlor1.3	0K / 2.6 GB	7	0
Flor1.3RAG	0K / 2.6 GB	7	1
CaBloom1.3 MultiQA	0K / 2.6 GB	13	0
CaBloom1.3 QA	0K / 2.6 GB	10	0
Bloom1.3 Meteo	0K / 2.6 GB	9	0
Hoa 1b4	0K / 5.2 GB	31	1
Bloom 1b5 Clp German	0K / 5.2 GB	23	9

Note: green Score (e.g. "73.2") means that the model is better than projecte-aina/FLOR-1.3B-Instructed.