# Multilingual text generation

A quantized version of Gama-12B, providing files of various quantization types, suitable for text generation tasks and supporting English and Portuguese.

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

A lightweight multilingual large language model distilled from OpenBuddy/Qwen3-32B, supporting 8 languages and using the Apache 2.0 license

A multilingual text generation model fine-tuned based on unsloth/Llama-3.3-70B-Instruct-bnb-4bit, supporting English, Spanish, Latin, Arabic, and French.

A quantized version based on the infly/inf-o1-pi0 model, supporting multilingual text generation tasks, optimized with llama.cpp's imatrix quantization.

A multilingual text generation model based on Mistral-Small-3.1-24B-Base-2503, supporting 10 languages, suitable for role-playing and dialogue scenarios

This is a 4-bit quantized language model in MLX format, suitable for text generation tasks.

Devstral-Small-2505-8bit is an 8-bit quantized model converted from mistralai/Devstral-Small-2505, suitable for the MLX framework and supporting text generation tasks in multiple languages.

Quantized version of Devstral-Small-2505, supporting multilingual text generation tasks, suitable for local deployment and inference.

Devstral-Small-2505-bf16 is an MLX-format model converted from MistralAI's Devstral-Small-2505 model, supporting multiple language processing tasks.

This is a 3-bit quantized version converted from the mistralai/Devstral-Small-2505 model, designed for the MLX framework and supports multilingual text generation tasks.

A lightweight language model developed by mistralai, optimized with 6-bit quantization via the MLX framework, specifically designed for Apple Silicon.

The Devstral-Small-2505 model developed by mistralai, optimized with MLX 4-bit quantization for Apple Silicon devices.

Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a range of dense and Mixture of Experts (MoE) models. Based on large-scale training, Qwen3 has achieved breakthrough progress in reasoning capabilities, instruction following, agent functionalities, and multilingual support.

Zeta 2 is a small language model (SLM) with approximately 460 million parameters, meticulously crafted on consumer-grade computers and supports multiple languages.

Qwen3-30B-A3B-abliterated is a 30 billion parameter large language model based on the Qwen architecture, focusing on text generation tasks.

Nous Consilience 40B is a 40-billion-parameter generative text model, pre-trained from scratch in a decentralized manner, supporting multiple languages and representing diverse human creative output.

Nous Consilience 40B is a generative text model pretrained in a decentralized manner via the internet, representing the diverse and extensive creative achievements of humanity.

This is a GGUF format model converted from kyutai/helium-1-2b, supporting multiple European languages.

Foundation-Sec-8B is a large language model based on the Transformer architecture, focusing on text generation tasks.

Plain text adaptation of Gemma 3 27B, removing image processing capabilities to focus on text generation tasks

Llama 3.3 Swallow is a large language model (70B) based on continuous pre-training of the Meta Llama 3.3 model, enhancing Japanese capabilities while retaining original English proficiency.

LaMini-Flan-T5-783M is a lightweight text generation model based on the T5 architecture, supporting English, Russian, and Ukrainian, suitable for various natural language processing tasks.

IndicBART-mr-test is a fine-tuned version of the ai4bharat/IndicBART model on an unknown dataset, primarily used for text generation tasks with support for Marathi.

This model is a GGUF format version converted from NVIDIA's Llama-3_3-Nemotron-Super-49B-v1, suitable for text generation tasks.

GGUF format model converted from VIDraft/Gemma-3-R1984-27B, supporting multilingual text generation

The ONNX version of TeapotLLM, supporting multilingual text generation models that run in the browser via Transformers.js.

Qwerky-QwQ-32B is a large language model with 32B parameters, specializing in text generation tasks.

Large language model based on Gemma2 architecture with 924 million parameters, supporting multilingual text generation tasks

A Chinese-English hybrid model based on the Gemma-2B architecture, integrating two specially optimized sub-models through the SLERP method

RWKV-7 model based on flash-linear attention format, supporting multilingual text generation tasks.

This is the quantized version of the Mistral-7B-Instruct-Uz model, supporting Uzbek and English, suitable for tasks like text generation, summarization, translation, and question answering.

This is the quantized version of LGAI-EXAONE's EXAONE-Deep-2.4B model, quantized using llama.cpp, supporting English and Korean text generation tasks.

Kanana Nano 2.1B Instruct is a 2.1 billion parameter instruction-finetuned language model developed by Kakao, supporting English and Korean text generation tasks.

A multilingual text generation model fine-tuned based on Qwen2.5-3B-Instruct, supporting 13 languages and doubling the training speed

GGUF format model converted from AtlaAI/Selene-1-Mini-Llama-3.1-8B, suitable for text generation tasks and supports multiple European languages.

This model is a text generation model capable of producing coherent text content based on input prompts.

This is the quantized version of the c4ai-command-r7b-12-2024-abliterated model, quantized using llama.cpp, supporting multiple quantization types and suitable for various hardware environments.

A multilingual reinforced language model fine-tuned based on the Qwen/Qwen2.5 - 32B - Instruct base model, proficient in multilingual processing and dealing with complex logical problems.

GGUF format model file of Meltemi-7B-Instruct-v1.5, suitable for Greek and English text generation tasks.