# Multilingual instruction fine-tuning

This is an MLX format model converted from Mistral-Small-3.2-24B-Instruct-2506, suitable for instruction following tasks.

Samastam is an early instruction-tuned variant of the Sarvam-1 model, fine-tuned on the Alpaca-cleaned dataset to support multilingual instruction responses.

Mistral-Small-24B-Instruct-2501 is a 24B-parameter instruction-finetuned large language model supporting multilingual text generation tasks.

A 70B-parameter large language model based on the Llama 3.3 architecture, supporting multilingual text generation tasks, optimized through quantization for various hardware environments

This is the quantized version of the original model meta-llama/Llama-4-Scout-17B-16E-Instruct, optimized with int4 quantization technology, suitable for multilingual tasks.

A 4-bit quantized model converted from meta-llama/Llama-4-Maverick-17B-128E-Instruct, supporting multilingual text generation tasks

A 24B-parameter instruction-tuned model based on Mistral Small 3.1, supporting multilingual and visual understanding, suitable for local deployment and efficient inference.

An ultra-low-bit (1-2 bit) quantized model based on Llama-3.1-70B, utilizing IQ-DynamicGate technology for adaptive precision quantization, enhancing accuracy while maintaining memory efficiency.

GaMS-9B-Instruct is a Slovenian generation model based on Google's Gemma 2 series, supporting Slovenian, English, and partially Croatian, Serbian, and Bosnian, with a focus on text generation tasks.

A merged model based on multiple Qwen series 32B parameter models, enhanced with Model Stock method for improved multilingual processing capabilities

A GGUF-format 2B-parameter multilingual instruction fine-tuned model supporting 30+ languages, suitable for text generation tasks.

This is the llamafied version of the EXAONE-3.5-32B-Instruct model developed by LG AI Research, a large language model supporting English and Korean.

A 3-billion parameter instruction-tuned language model developed by IBM, based on Granite-3.0 architecture, supporting multilingual tasks and commercial applications

Llama 3.2 is a 3-billion-parameter instruction-fine-tuned large language model released by Meta, supporting multilingual text generation tasks

This is Meta's 1 billion parameter instruction-tuned model from the Llama 3.2 series, converted to GGUF format for use with llama.cpp

Mistral-Nemo-Instruct-2407 is a large language model fine-tuned on instructions based on Mistral-Nemo-Base-2407, jointly trained by Mistral AI and NVIDIA, outperforming existing models of similar or smaller size.

Aya 23 is an instruction-fine-tuned open-weight research version model with highly advanced multilingual capabilities, supporting 23 languages.

A multilingual hybrid model based on Llama-3-8b, integrating German, Italian, and English capabilities

Multilingual instruction model fine-tuned on Gemma-2b, supporting 15 Indian languages and English

BigTranslate is a multilingual translation model enhanced based on LLaMA-13B, supporting translation tasks in over 100 languages.

The 4-bit quantized version of Falcon-7B-Instruct, quantized using the AutoGPTQ tool, suitable for efficient inference in resource-constrained environments.

FLAN-T5 XXL is a variant of Google's T5 model, fine-tuned on over 1,000 additional tasks, supports multiple languages, and outperforms the original T5 model.