Gama-12B-GGUF Open-Source Large Language Model - Multilingual Support and Multiple Quantization Versions to Meet Diverse Needs

Gama 12b GGUF

Developed by mradermacher

Gama-12B is a large language model supporting multiple languages, offering various quantized versions to meet different performance and precision requirements.

Large Language Model

Transformers

Supports Multiple Languages#Multilingual text generation #High-precision quantization #Dialogue system optimization

Downloads 185

Release Time : 6/22/2025

Model Overview

This project provides a static quantized version of the Gama-12B model, supporting English and Portuguese, suitable for text generation and dialogue tasks.

Model Features

Multilingual support

Supports text generation and dialogue in both English and Portuguese.

Multiple quantization types

Provides various quantized versions from Q2_K to Q8_0 to meet different performance and precision requirements.

Model fusion

Fuses the features of multiple excellent models, including Gemma-3-Glitter-12B, etc.

Model Capabilities

Text generation

Multilingual dialogue

Quantized inference

Use Cases

Natural language processing

Multilingual chatbot

Build a dialogue system supporting English and Portuguese.

Text generation

Used for content creation, story generation and other tasks.

🚀 Gama-12B Quantized Model

This project offers static quantizations of the rodrigomt/gama-12b model, providing various GGUF quantized versions for efficient text generation and conversational tasks.

🚀 Quick Start

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi - part files.

✨ Features

Multiple Languages: Supports both English (en) and Portuguese (pt).
Quantized Variants: Offers a range of quantized models with different sizes and qualities.
Merge of Models: Incorporates tags related to model merging, including allura-org/Gemma-3-Glitter-12B, soob3123/amoral-gemma3-12B-v2-qat, and soob3123/Veiled-Calla-12B.

📦 Installation

No specific installation steps are provided in the original document.

📚 Documentation

About

Static quants of https://huggingface.co/rodrigomt/gama-12b. Weighted/imatrix quants are available at https://huggingface.co/mradermacher/gama-12b-i1-GGUF.

Provided Quants

(sorted by size, not necessarily quality. IQ - quants are often preferable over similar sized non - IQ quants)

Link	Type	Size/GB	Notes
GGUF	Q2_K	4.9
GGUF	Q3_K_S	5.6
GGUF	Q3_K_M	6.1	lower quality
GGUF	Q3_K_L	6.6
GGUF	IQ4_XS	6.7
GGUF	Q4_K_S	7.0	fast, recommended
GGUF	Q4_K_M	7.4	fast, recommended
GGUF	Q5_K_S	8.3
GGUF	Q5_K_M	8.5
GGUF	Q6_K	9.8	very good quality
GGUF	Q8_0	12.6	fast, best quality

Here is a handy graph by ikawrakow comparing some lower - quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

📄 License

The model is licensed under gemma.

Property	Details
Base Model	rodrigomt/gama-12b
Language	en, pt
Library Name	transformers
License	gemma
Quantized By	mradermacher
Tags	merge, gemma, text - generation, conversational, allura - org/Gemma - 3 - Glitter - 12B, soob3123/amoral - gemma3 - 12B - v2 - qat, soob3123/Veiled - Calla - 12B

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご