# Multilingual assistant

Qwen2.5 is the latest series of Tongyi large language models, offering a variety of models with parameters ranging from 500 million to 72 billion, with significant improvements in coding, math, instruction following, and long text processing.

Qwen2.5 is the latest version of the Qwen large model series, a 0.5B parameter instruction-tuned model supporting 29+ languages and long-text generation.

Llama 4 Scout is a native multimodal AI model launched by Meta, supporting multilingual text and image understanding. It adopts the Mixture of Experts architecture and has industry-leading performance in text and image understanding.

INT8 quantized version of Qwen2.5-7B-Instruct, suitable for multilingual scenarios in both commercial and research applications, optimized for memory requirements and computational throughput.

FP8 quantized version of Llama-3.2-1B-Instruct, suitable for multilingual business and research applications, with performance close to the original model.

FP8 quantized version of Llama-3.2-3B-Instruct, suitable for multilingual commercial and research purposes, particularly ideal for assistant-like chat scenarios.

FP8 quantized version of Meta-Llama-3.1-405B-Instruct, suitable for multilingual commercial and research purposes, specially optimized for assistant robot scenarios.

FP8 quantized version of Meta-Llama-3.1-70B-Instruct, suitable for multilingual commercial and research purposes, especially ideal for assistant-like chat scenarios.

FP8 quantized version of Meta-Llama-3.1-8B-Instruct, suitable for multilingual business and research applications, specially optimized for assistant-like chat scenarios.

Meta Llama 3.1 is a multilingual large language model collection, including 8B, 70B, and 405B parameter pre-trained and instruction-tuned generative models, supporting 8 languages with outstanding performance on industry benchmarks.