# FP8 Efficient Inference

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

Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a full range of dense models and mixture-of-experts (MoE) models, achieving breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.

Qwen3-4B-FP8 is the latest large language model in the Qwen series, offering a 4-billion-parameter FP8 quantized version that supports switching between thinking and non-thinking modes, excelling in reasoning, instruction following, and agent capabilities.

An anime-style adapter based on Tencent's Hunyuan Video model, providing high-quality text-to-video generation capabilities, specifically optimized for anime-style content creation.

FLUX.1-dev is a text-to-image generation model based on the diffusers library, focusing on FP8 floating-point optimization during the development phase, capable of generating realistic and photorealistic images.

FLUX.1-dev is an experimental text-to-image generation model focused on photorealistic, realistic-style image generation.