Tongyi Deep Research, the Leading Open-source Deep Research Agent
Tongyi Qwen Aliyun Dashscope API Golang implementation, non-official
Run Z-Image-Turbo locally on Apple Silicon (M1/M2/M3/M4) with just two commands. MPS-optimized, Gradio UI, bilingual support.
Enable local integration of Qwen3.5 models with ComfyUI for text generation and multimodal visual tasks, featuring automatic model management and precision control.
FunASR最新语音识别模型Fun-ASR-Nano-2512实时识别热词版
🖼️ Enhance images effortlessly by adding or removing objects with the Qwen-Image-Edit-Object-Manipulator, ensuring realism and background detail.
🎨 Edit images in real-time using the Qwen-Image-Edit-2509 model with up to 20x speed improvements through StreamDiffusion-inspired technology.
Run local LLMs on RTX 3090 hardware with validated configs for vLLM, llama.cpp, and SGLang. Use optimized setups for high throughput or long-context stability.
Accelerate Qwen3.5 KVCache with TurboQuant MLX-LM tools for prompt caching, quantized attention, and research-ready evals
🚀 Achieve faster Qwen3-0.6B inference with the MegaQwen CUDA megakernel, delivering 531 tok/s decode on RTX 3090—3.9x faster than HuggingFace.
Run Qwen3.6-27B models on a single RTX 3090 GPU using optimized inference configs. See club-3090 for active developments and updated configurations.
Add a description, image, and links to the tongyi topic page so that developers can more easily learn about it.
To associate your repository with the tongyi topic, visit your repo's landing page and select "manage topics."