# Multilingual Dialogue

Qwen3-4B is the latest generation large language model in the Qwen series, featuring 4B parameters, supporting a 128k context window and over 100 languages, with outstanding performance in reasoning, instruction following, and agent capabilities.

Qwen3-1.7B-Q8_0-GGUF is a GGUF-format model converted from Qwen/Qwen3-1.7B, supporting text generation tasks with multilingual capabilities and efficient reasoning.

This is a 12B-parameter multilingual large language model fused using the SLERP method, supporting English and Japanese processing.

This repository contains GGUF format model files of JungZoona/T3Q-qwen2.5-14b-v1.0-e3, quantized by TensorBlock's machine and compatible with llama.cpp.

MiniCPM-S-1B-sft is a 1B-parameter language model optimized with activation sparsity techniques, achieving high-sparsity inference acceleration through the ProSparse method while maintaining performance comparable to the original model.

Qwen2.5 is the latest series of the Qwen large language model, featuring a 1.5B parameter instruction-tuned model that supports multilingual and long text generation.

Kyro-n1.1 is an enhanced version of Kyro-n1, built upon Qwen2.5-7B-Instruct, with optimized reasoning capabilities, comprehension, and response accuracy.

The Meta Llama 3.1 series is a collection of multilingual large language models (LLMs), including pre-trained and instruction-tuned generative models in 8B, 70B, and 405B sizes. The 8B version is optimized for multilingual dialogue use cases and excels in common benchmarks.

The Elastic Model is a series of models generated by TheStage AI ANNA, allowing free adjustment of model scale, latency, and quality through a sliding control bar, providing the fastest and most flexible solution for self-hosting scenarios.

HMS-Slerp-12B is a multilingual chat model merged using the SLERP (Spherical Linear Interpolation) method, supporting both English and Japanese.

A ChatML-formatted language model merged from the ElvenMaid-12B series, supporting English and Japanese

ElvenMaid-12B is a 12B-parameter language model based on the ChatML format, created by merging multiple pre-trained models using the mergekit tool, supporting interactions in both English and Japanese.

Himeyuri-Magnum-12B is a multilingual pre-trained language model based on the ChatML format, created by merging multiple 12B-parameter models using the mergekit tool.

A large language model based on the Phi 4 architecture, with 14 billion parameters, optimized for natural language processing and text dialogue tasks.

The Trillion-7B Preview is a multilingual large language model supporting English, Korean, Japanese, and Chinese. It outperforms other 7B-scale models in computational efficiency and performance.

The Trillion-7B Preview is a multilingual large language model supporting English, Korean, Japanese, and Chinese. It achieves performance competitive with higher-computation models while maintaining lower computational requirements.

A dialogue model based on the ChatML architecture, generated by merging pre-trained language models using the mergekit tool

Kyro-n1.1 is an enhanced version of Kyro-n1, built upon Qwen2.5-7B-Instruct, with optimized reasoning capabilities, comprehension, and response accuracy.

A multilingual ChatML model merged using the SCE method, supporting English and Japanese dialogue

Fibonacci-1-EN-8b-Chat.P1_5 is a large language model based on the LLaMA architecture, with 8.03 billion parameters, optimized for natural language processing tasks and text dialogue.

Quantized version based on ozone-ai/0x-lite model, supporting Chinese and English text generation tasks, using llama.cpp for imatrix quantization, offering multiple quantization options to adapt to different hardware requirements.

This is a quantized version of Llama-3.3-70B-Instruct. It supports multilingual text generation and can be used in commercial and research scenarios, performing excellently in multiple benchmark tests.

Razorback 12B v0.2 is a multimodal model combining the strengths of Pixtral 12B and UnslopNemo v3, featuring visual understanding and language processing capabilities.

GGUF format model file of OpenBuddy/openbuddy-deepseek-10b-v17.1-4k, supporting multiple languages, suitable for text generation tasks.

Llama 3.3 70B Instruct AWQ INT4 is the 4-bit quantized version of the Meta Llama 3.3 70B Instruct model, optimized for multilingual dialogue use cases and text generation tasks.

GLM-4-9B is the latest open-source version of the GLM-4 series pre-trained model developed by Zhipu AI, featuring exceptional capabilities in semantics, mathematics, reasoning, coding, and knowledge.

A large language model fine-tuned on multilingual datasets based on Qwen/Qwen2.5-7B, supporting 13 language processing

Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.

This is the INT4 quantized version of the Meta-Llama-3.1-8B-Instruct model, quantized using the GPTQ algorithm, suitable for multilingual dialogue scenarios.

GGUF quantized version of Meta Llama 3.1 8B instruction-tuned model, suitable for multilingual dialogue scenarios

INT4 quantized version of Llama 3.1 70B Instruct, optimized with AutoAWQ technology, suitable for multilingual dialogue scenarios.

INT4 quantized version of Llama 3.1 8B Instruct, quantized using AutoAWQ tool, suitable for multilingual dialogue scenarios.

Yuna AI is a virtual companion model designed for emotional connection, offering deep interactive experiences beyond traditional assistants.

Bllossom is a Korean-English bilingual language model based on Llama3, enhanced through comprehensive tuning to improve Korean language capabilities, expanding Korean vocabulary and optimizing Korean context processing.

Suzume 8B is a multilingual fine-tuned version based on Llama 3, trained on nearly 90,000 multilingual dialogues to enhance multilingual communication capabilities while maintaining Llama 3's intelligence level.

WizardLM-2 7B is a highly efficient large language model developed by Microsoft AI team, based on the Mistral-7B architecture, excelling in multilingual, reasoning, and agent tasks.

WizardLM-2 8x22B is the next-generation state-of-the-art large language model developed by Microsoft AI, featuring a Mixture of Experts (MoE) architecture, excelling in complex dialogue, multilingual capabilities, reasoning, and agent tasks.

GGUF quantized version of WizardLM-2-7B, developed by Microsoft AI WizardLM team, supports multilingual text generation tasks

An instruction fine-tuned large language model based on DictaLM-2.0, specifically optimized for Hebrew and English chat scenarios

Calme-7B is a 7-billion-parameter language model fine-tuned based on Mistral-7B, excelling in generating clear, peaceful, and coherent text.